Felice Andrea Pellegrino, Franco Blanchini, Gianfranco Fenu and Erica Salvato.
Closed-loop Control from Data-Driven Open-Loop Optimal Control Trajectories.
In Alessandro Astolfi and Thomas Parisini (eds.). 2022 European Control Conference (ECC) 1(1). July 2022, 1379–1384.
Abstract We show how the recent works on data driven open-loop minimum-energy control for linear systems can be exploited to obtain closed-loop piecewise-affine control laws, by employing a state-space partitioning technique which is at the basis of the static relatively optimal control. In addition, we propose a way for employing portions of the experimental input and state trajectories to recover information about the natural movement of the state and dealing with non-zero initial conditions. The same idea can be used for formulating several open-loop control problems entirely based on data, possibly including input and state constraints. URL, DOI BibTeX
@inproceedings{Pellegrino2022ECC,
abstract = "We show how the recent works on data driven open-loop minimum-energy control for linear systems can be exploited to obtain closed-loop piecewise-affine control laws, by employing a state-space partitioning technique which is at the basis of the static relatively optimal control. In addition, we propose a way for employing portions of the experimental input and state trajectories to recover information about the natural movement of the state and dealing with non-zero initial conditions. The same idea can be used for formulating several open-loop control problems entirely based on data, possibly including input and state constraints.",
address = "London",
author = "Pellegrino, Felice Andrea and Blanchini, Franco and Fenu, Gianfranco and Salvato, Erica",
booktitle = "2022 European Control Conference (ECC)",
doi = "10.23919/ECC55457.2022.9838344",
editor = "Astolfi, Alessandro and Parisini, Thomas",
isbn = 9783907144077,
month = "jul",
number = 1,
pages = "1379--1384",
publisher = "EUCA",
title = "{Closed-loop Control from Data-Driven Open-Loop Optimal Control Trajectories}",
url = "https://ieeexplore.ieee.org/document/9838344",
volume = 1,
year = 2022
}
Benedetta Liberatori, Ciro Antonio Mami, Giovanni Santacatterina, Marco Zullich and Felice Andrea Pellegrino.
YOLO-Based Face Mask Detection on Low-End Devices Using Pruning and Quantization.
In Karolj Skala (ed.). 2022 45th International Convention on Information, Communication and Electronic Technology (MIPRO). May 2022, 900–905.
Abstract Deploying Deep Learning (DL) based object detection (OD) models in low-end devices, such as single board computers, may lead to poor performance in terms of frames-per-second (FPS). Pruning and quantization are well-known compression techniques that can potentially lead to a reduction of the computational burden of a DL model, with a possible decrease of performance in terms of detection accuracy. Motivated by the widespread introduction of face mask mandates by many institutions during the Covid-19 pandemic, we aim at training and compressing an OD model based on YOLOv4 to recognize the presence of face masks, to be deployed on a Raspberry Pi 4. We investigate the capability of different kinds of pruning and quantization techniques of increasing the FPS with respect to the uncompressed model, while retaining the detection accuracy. We quantitatively assess the pruned and quantized models in terms of Mean Average Precision (mAP) and FPS, and show that with proper pruning and quantization, the FPS can be doubled with a moderate loss in mAP. The results provide guidelines for compression of other OD models based on YOLO. URL, DOI BibTeX
@inproceedings{Liberatori2022,
abstract = "Deploying Deep Learning (DL) based object detection (OD) models in low-end devices, such as single board computers, may lead to poor performance in terms of frames-per-second (FPS). Pruning and quantization are well-known compression techniques that can potentially lead to a reduction of the computational burden of a DL model, with a possible decrease of performance in terms of detection accuracy. Motivated by the widespread introduction of face mask mandates by many institutions during the Covid-19 pandemic, we aim at training and compressing an OD model based on YOLOv4 to recognize the presence of face masks, to be deployed on a Raspberry Pi 4. We investigate the capability of different kinds of pruning and quantization techniques of increasing the FPS with respect to the uncompressed model, while retaining the detection accuracy. We quantitatively assess the pruned and quantized models in terms of Mean Average Precision (mAP) and FPS, and show that with proper pruning and quantization, the FPS can be doubled with a moderate loss in mAP. The results provide guidelines for compression of other OD models based on YOLO.",
address = "Opatija",
author = "Liberatori, Benedetta and Mami, Ciro Antonio and Santacatterina, Giovanni and Zullich, Marco and Pellegrino, Felice Andrea",
booktitle = "2022 45th International Convention on Information, Communication and Electronic Technology (MIPRO)",
doi = "10.23919/MIPRO55190.2022.9803406",
editor = "Skala, Karolj",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Liberatori et al. - 2022 - YOLO-Based Face Mask Detection on Low-End Devices Using Pruning and Quantization.pdf:pdf",
keywords = "deep learning,face mask detection,object detection,pruning,quantization,tinyml,yolo",
month = "may",
pages = "900--905",
publisher = "Croatian Society MIPRO",
title = "{YOLO-Based Face Mask Detection on Low-End Devices Using Pruning and Quantization}",
url = "https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9803406",
year = 2022
}
Giorgia Nadizar, Eric Medvet, Felice Andrea Pellegrino, Marco Zullich and Stefano Nichele.
On the Effects of Pruning on Evolved Neural Controllers for Soft Robots.
In Proceedings of the Genetic and Evolutionary Computation Conference Companion. 2021, 1744–1752.
Abstract Artificial neural networks (ANNs) are commonly used for controlling robotic agents. For robots with many sensors and actuators, ANNs can be very complex, with many neurons and connections. Removal of neurons or connections, i.e., pruning, may be desirable because (a) it reduces the complexity of the ANN, making its operation more energy efficient, and (b) it might improve the generalization ability of the ANN. Whether these goals can actually be achieved in practice is however still not well known. On the other hand, it is widely recognized that pruning in biological neural networks plays a fundamental role in the development of brains and their ability to learn. In this work, we consider the case of Voxel-based Soft Robots, a kind of robots where sensors and actuators are distributed over the body and that can be controlled with ANNs optimized by means of neuroevolution. We experimentally characterize the effect of different forms of pruning on the effectiveness of neuroevolution, also in terms of generalization ability of the evolved ANNs. We find that, with some forms of pruning, a large portion of the connections can be pruned without strongly affecting robot capabilities. We also observe sporadic improvements in generalization ability. URL, DOI BibTeX
@inproceedings{Nadizar2021,
abstract = "Artificial neural networks (ANNs) are commonly used for controlling robotic agents. For robots with many sensors and actuators, ANNs can be very complex, with many neurons and connections. Removal of neurons or connections, i.e., pruning, may be desirable because (a) it reduces the complexity of the ANN, making its operation more energy efficient, and (b) it might improve the generalization ability of the ANN. Whether these goals can actually be achieved in practice is however still not well known. On the other hand, it is widely recognized that pruning in biological neural networks plays a fundamental role in the development of brains and their ability to learn. In this work, we consider the case of Voxel-based Soft Robots, a kind of robots where sensors and actuators are distributed over the body and that can be controlled with ANNs optimized by means of neuroevolution. We experimentally characterize the effect of different forms of pruning on the effectiveness of neuroevolution, also in terms of generalization ability of the evolved ANNs. We find that, with some forms of pruning, a large portion of the connections can be pruned without strongly affecting robot capabilities. We also observe sporadic improvements in generalization ability.",
address = "New York, NY, USA",
author = "Nadizar, Giorgia and Medvet, Eric and Pellegrino, Felice Andrea and Zullich, Marco and Nichele, Stefano",
booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference Companion",
doi = "10.1145/3449726.3463161",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Nadizar et al. - 2021 - On the Effects of Pruning on Evolved Neural Controllers for Soft Robots.pdf:pdf",
isbn = 9781450383516,
keywords = "evolutionary robotics,neuroevolution,synaptic pruning",
pages = "1744--1752",
publisher = "Association for Computing Machinery",
series = "GECCO '21",
title = "{On the Effects of Pruning on Evolved Neural Controllers for Soft Robots}",
url = "https://doi.org/10.1145/3449726.3463161",
year = 2021
}
Marco Zullich, Eric Medvet, Felice Andrea Pellegrino and Alessio Ansuini.
Speeding-up pruning for Artificial Neural Networks: Introducing Accelerated Iterative Magnitude Pruning.
In Rita Cucchiara, Alberto Del Bimbo and Stan Sclaroff (eds.). 2020 25th International Conference on Pattern Recognition (ICPR). January 2021, 3868–3875.
Abstract In recent years, Artificial Neural Networks (ANNs) pruning has become the focal point of many researches, due to the extreme overparametrization of such models. This has urged the scientific world to investigate methods for the simplification of the structure of weights in ANNs, mainly in an effort to reduce time for both training and inference. Frankle and Carbin [1], and later Renda, Frankle, and Carbin [2] introduced and refined an iterative pruning method which is able to effectively prune the network of a great portion of its parameters with little to no loss in performance. On the downside, this method requires a large amount of time for its application, since, for each iteration, the network has to be trained for (almost) the same amount of epochs of the unpruned network. In this work, we show that, for a limited setting, if targeting high overall sparsity rates, this time can be effectively reduced for each iteration, save for the last one, by more than 50%, while yielding a final product (i.e., final pruned network) whose performance is comparable to the ANN obtained using the existing method. DOI BibTeX
@inproceedings{Zullich2021ICPR,
abstract = "In recent years, Artificial Neural Networks (ANNs) pruning has become the focal point of many researches, due to the extreme overparametrization of such models. This has urged the scientific world to investigate methods for the simplification of the structure of weights in ANNs, mainly in an effort to reduce time for both training and inference. Frankle and Carbin [1], and later Renda, Frankle, and Carbin [2] introduced and refined an iterative pruning method which is able to effectively prune the network of a great portion of its parameters with little to no loss in performance. On the downside, this method requires a large amount of time for its application, since, for each iteration, the network has to be trained for (almost) the same amount of epochs of the unpruned network. In this work, we show that, for a limited setting, if targeting high overall sparsity rates, this time can be effectively reduced for each iteration, save for the last one, by more than 50%, while yielding a final product (i.e., final pruned network) whose performance is comparable to the ANN obtained using the existing method.",
address = "Milan",
author = "Zullich, Marco and Medvet, Eric and Pellegrino, Felice Andrea and Ansuini, Alessio",
booktitle = "2020 25th International Conference on Pattern Recognition (ICPR)",
doi = "10.1109/icpr48806.2021.9412705",
editor = "Cucchiara, Rita and {Del Bimbo}, Alberto and Sclaroff, Stan",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Zullich et al. - 2021 - Speeding-up pruning for Artificial Neural Networks Introducing Accelerated Iterative Magnitude Pruning.pdf:pdf",
isbn = 9781728188089,
month = "jan",
pages = "3868--3875",
publisher = "IEEE",
title = "{Speeding-up pruning for Artificial Neural Networks: Introducing Accelerated Iterative Magnitude Pruning}",
year = 2021
}
Erica Salvato, Gianfranco Fenu, Eric Medvet and Felice Andrea Pellegrino.
Characterization of Modeling Errors Affecting Performances of a Robotics Deep Reinforcement Learning Controller in a Sim-to-Real Transfer.
In 2021 44th International Convention on Information, Communication and Electronic Technology (MIPRO) (1). 2021, 1154–1159.
Abstract Simulation is a powerful tool used to train Re- inforcement Learning (RL) agents involved in robotic tasks. It allows to collect large amount of data in comparatively faster and safer way than on the real robot. However, a simulator is only an approximation of the physical system to be controlled. Due to modeling errors, a controller learned on the simulator dynamics may behave differently once applied to the real robot. In the worst case, the controller, although being successful when applied on the simulator, may fail when applied on the real platform. In this paper, we deal with the sim-to-real transfer of a RL controller for a Poppy Ergo-Jr robotic arm involved in a positioning task: i.e., moving the servo joints in order to reach a desired target position with the end-effector. In particular, we want to investigate the differences between the real robot and its simulator and how they affect the controller performance after its transfer from the simulator to the real platform. URL, DOI BibTeX
@inproceedings{Salvato2021MIPRO,
abstract = "Simulation is a powerful tool used to train Re- inforcement Learning (RL) agents involved in robotic tasks. It allows to collect large amount of data in comparatively faster and safer way than on the real robot. However, a simulator is only an approximation of the physical system to be controlled. Due to modeling errors, a controller learned on the simulator dynamics may behave differently once applied to the real robot. In the worst case, the controller, although being successful when applied on the simulator, may fail when applied on the real platform. In this paper, we deal with the sim-to-real transfer of a RL controller for a Poppy Ergo-Jr robotic arm involved in a positioning task: i.e., moving the servo joints in order to reach a desired target position with the end-effector. In particular, we want to investigate the differences between the real robot and its simulator and how they affect the controller performance after its transfer from the simulator to the real platform.",
author = "Salvato, Erica and Fenu, Gianfranco and Medvet, Eric and Pellegrino, Felice Andrea",
booktitle = "2021 44th International Convention on Information, Communication and Electronic Technology (MIPRO)",
doi = "10.23919/MIPRO52101.2021.9596864",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Salvato et al. - 2021 - Characterization of Modeling Errors Affecting Performances of a Robotics Deep Reinforcement Learning Controller.pdf:pdf",
isbn = 9789532331011,
keywords = "model-,reinforcement learning,sim-to-real",
number = 1,
pages = "1154--1159",
publisher = "Croatian Society MIPRO",
title = "{Characterization of Modeling Errors Affecting Performances of a Robotics Deep Reinforcement Learning Controller in a Sim-to-Real Transfer}",
url = "https://ieeexplore.ieee.org/document/9596864",
year = 2021
}
Felice Andrea Pellegrino and Walter Vanzella.
Virtual Redundancy and Barrier Functions for Collision Avoidance in Robotic Manufacturing.
In Josef Jablonsky, Michel Fliess and Enrique H Viedma (eds.). 2020 7th International Conference on Control, Decision and Information Technologies (CoDIT) 1. June 2020, 957–962.
Abstract In some robotic manufacturing processes, a displacement between the nominal tool trajectory and the actual can be tolerated, provided that the displacement occurs along a specific direction/rotation axis. For instance, in wire sawing, a translation along the wire axis is permitted. Such an admissible displacement can be thought of as an additional degree of freedom that could be exploited for accomplishing further tasks, e.g., collision avoidance. In the case of offline programming, the operator can manually adapt the trajectory in order to exploit such additional degree of freedom. However, when the tool trajectory is automatically generated, as in modern flexible automation systems, an automatic way to adjust the displacement is needed. We propose an approach that, based on virtual redundancy (introduced originally for singularity avoidance purposes) and barrier functions, can automatically exploit the additional degree of freedom while satisfying the constraints on the admissible displacement. URL, DOI BibTeX
@inproceedings{Pellegrino2020,
abstract = "In some robotic manufacturing processes, a displacement between the nominal tool trajectory and the actual can be tolerated, provided that the displacement occurs along a specific direction/rotation axis. For instance, in wire sawing, a translation along the wire axis is permitted. Such an admissible displacement can be thought of as an additional degree of freedom that could be exploited for accomplishing further tasks, e.g., collision avoidance. In the case of offline programming, the operator can manually adapt the trajectory in order to exploit such additional degree of freedom. However, when the tool trajectory is automatically generated, as in modern flexible automation systems, an automatic way to adjust the displacement is needed. We propose an approach that, based on virtual redundancy (introduced originally for singularity avoidance purposes) and barrier functions, can automatically exploit the additional degree of freedom while satisfying the constraints on the admissible displacement.",
address = "Prague",
author = "Pellegrino, Felice Andrea and Vanzella, Walter",
booktitle = "2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)",
doi = "10.1109/CoDIT49905.2020.9263936",
editor = "Jablonsky, Josef and Fliess, Michel and Viedma, Enrique H.",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Pellegrino, Vanzella - 2020 - Virtual Redundancy and Barrier Functions for Collision Avoidance in Robotic Manufacturing(2).pdf:pdf",
issn = "2576-3555",
keywords = "Collision avoidance,Kinematics,Redundancy,Robot kinematics,Robots,Task analysis,Trajectory",
month = "jun",
pages = "957--962",
publisher = "IEEE",
title = "{Virtual Redundancy and Barrier Functions for Collision Avoidance in Robotic Manufacturing}",
url = "https://ieeexplore.ieee.org/document/9263936",
volume = 1,
year = 2020
}
Alessio Ansuini, Eric Medvet, Felice Andrea Pellegrino and Marco Zullich.
On the Similarity between Hidden Layers of Pruned and Unpruned Convolutional Neural Networks.
In Maria De Marsico, Gabriella Sanniti di Baja and Ana Fred (eds.). Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2020). February 2020, 52–59.
Abstract During the last few decades, artificial neural networks (ANN) have achieved an enormous success in regres- sion and classification tasks. The empirical success has not been matched with an equally strong theoretical understanding of such models, as some of their working principles (training dynamics, generalization proper- ties, and the structure of inner representations) still remain largely unknown. It is, for example, particularly difficult to reconcile the well known fact that ANNs achieve remarkable levels of generalization also in con- ditions of severe over-parametrization. In our work, we explore a recent network compression technique, called Iterative Magnitude Pruning (IMP), and apply it to convolutional neural networks (CNN). The pruned and unpruned models are compared layer-wise with Canonical Correlation Analysis (CCA). Our results show a high similarity between layers of pruned and unpruned CNNs in the first convolutional layers and in the fully-connected layer, while for the intermediate convolutional layers the similarity is significantly lower. This suggests that, although in intermediate layers representation in pruned and unpruned networks is markedly different, in the last part the fully-connected layers act as pivots, producing not only similar performances but also similar representations of the data, despite the large difference in the number of parameters involved. DOI BibTeX
@inproceedings{Ansuini2020,
abstract = "During the last few decades, artificial neural networks (ANN) have achieved an enormous success in regres- sion and classification tasks. The empirical success has not been matched with an equally strong theoretical understanding of such models, as some of their working principles (training dynamics, generalization proper- ties, and the structure of inner representations) still remain largely unknown. It is, for example, particularly difficult to reconcile the well known fact that ANNs achieve remarkable levels of generalization also in con- ditions of severe over-parametrization. In our work, we explore a recent network compression technique, called Iterative Magnitude Pruning (IMP), and apply it to convolutional neural networks (CNN). The pruned and unpruned models are compared layer-wise with Canonical Correlation Analysis (CCA). Our results show a high similarity between layers of pruned and unpruned CNNs in the first convolutional layers and in the fully-connected layer, while for the intermediate convolutional layers the similarity is significantly lower. This suggests that, although in intermediate layers representation in pruned and unpruned networks is markedly different, in the last part the fully-connected layers act as pivots, producing not only similar performances but also similar representations of the data, despite the large difference in the number of parameters involved.",
address = "La Valletta",
author = "Ansuini, Alessio and Medvet, Eric and Pellegrino, Felice Andrea and Zullich, Marco",
booktitle = "Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2020)",
doi = "10.5220/0008960300520059",
editor = "{De Marsico}, Maria and {Sanniti di Baja}, Gabriella and Fred, Ana",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Ansuini et al. - 2020 - On the Similarity between Hidden Layers of Pruned and Unpruned Convolutional Neural Networks.pdf:pdf",
isbn = 9789897583971,
month = "feb",
pages = "52--59",
publisher = "Scitepress",
title = "{On the Similarity between Hidden Layers of Pruned and Unpruned Convolutional Neural Networks}",
year = 2020
}
Gianfranco Fenu, Eric Medvet, Daniele Panfilo and Felice Andrea Pellegrino.
Mosaic Images Segmentation using U-net.
In Maria De Marsico, Gabriella Sanniti di Baja and Ana Fred (eds.). Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2020). February 2020, 485–492.
Abstract We consider the task of segmentation of images of mosaics, where the goal is to segment the image in such a way that each region corresponds exactly to one tile of the mosaic. We propose to use a recent deep learning technique based on a kind of convolutional neural networks, called U-net, that proved to be effective in seg- mentation tasks. Our method includes a preprocessing phase that allows to learn a U-net despite the scarcity of labeled data, which reflects the peculiarity of the task, in which manual annotation is, in general, costly. We experimentally evaluate our method and compare it against the few other methods for mosaic images segmen- tation using a set of performance indexes, previously proposed for this task, computed using 11 images of real mosaics. In our results, U-net compares favorably with previous methods. Interestingly, the considered meth- ods make errors of different kinds, consistently with the fact that they are based on different assumptions and techniques. This finding suggests that combining different approaches might lead to an even more effective segmentation. DOI BibTeX
@inproceedings{Fenu2020,
abstract = "We consider the task of segmentation of images of mosaics, where the goal is to segment the image in such a way that each region corresponds exactly to one tile of the mosaic. We propose to use a recent deep learning technique based on a kind of convolutional neural networks, called U-net, that proved to be effective in seg- mentation tasks. Our method includes a preprocessing phase that allows to learn a U-net despite the scarcity of labeled data, which reflects the peculiarity of the task, in which manual annotation is, in general, costly. We experimentally evaluate our method and compare it against the few other methods for mosaic images segmen- tation using a set of performance indexes, previously proposed for this task, computed using 11 images of real mosaics. In our results, U-net compares favorably with previous methods. Interestingly, the considered meth- ods make errors of different kinds, consistently with the fact that they are based on different assumptions and techniques. This finding suggests that combining different approaches might lead to an even more effective segmentation.",
address = "La Valletta",
author = "Fenu, Gianfranco and Medvet, Eric and Panfilo, Daniele and Pellegrino, Felice Andrea",
booktitle = "Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2020)",
doi = "10.5220/0008967404850492",
editor = "{De Marsico}, Maria and {Sanniti di Baja}, Gabriella and Fred, Ana",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Fenu et al. - 2020 - Mosaic Images Segmentation using U-net.pdf:pdf",
isbn = 9789897583971,
month = "feb",
pages = "485--492",
publisher = "Scitepress",
title = "{Mosaic Images Segmentation using U-net}",
year = 2020
}
Alexander Babichev, Vittorio Casagrande, Luca Della Schiava, Gianfranco Fenu, Imola Fodor, Enrico Marson, Felice Andrea Pellegrino, Gilberto Pin, Erica Salvato, Michele Toppano and Davide Zorzenon.
Loads Estimation using Deep Learning Techniques in Consumer Washing Machines.
In Maria De Marsico, Gabriella Sanniti di Baja and Ana Fred (eds.). Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods. February 2020, 425–432.
Abstract Home appliances are nowadays present in every house. In order to ensure a suitable level of maintenance, manufacturers strive to design a method to estimate the wear of the single electrical parts composing an appliance without providing it with a large number of expensive sensors. With this in mind, our goal consists in inferring the status of the electrical actuators of a washing machine, given the measures of electrical signals at the plug, which carry an aggregate information. The approach is end-to-end, i.e. it does not require any feature extraction and thus it can be easily generalized to other appliances. Two different techniques have been investigated: Convolutional Neural Networks and Long Short-Term Memories. These tools are trained and tested on data collected on four different washing machines. URL, DOI BibTeX
@inproceedings{Babichev2020,
abstract = "Home appliances are nowadays present in every house. In order to ensure a suitable level of maintenance, manufacturers strive to design a method to estimate the wear of the single electrical parts composing an appliance without providing it with a large number of expensive sensors. With this in mind, our goal consists in inferring the status of the electrical actuators of a washing machine, given the measures of electrical signals at the plug, which carry an aggregate information. The approach is end-to-end, i.e. it does not require any feature extraction and thus it can be easily generalized to other appliances. Two different techniques have been investigated: Convolutional Neural Networks and Long Short-Term Memories. These tools are trained and tested on data collected on four different washing machines.",
address = "La Valletta",
author = "Babichev, Alexander and Casagrande, Vittorio and {Della Schiava}, Luca and Fenu, Gianfranco and Fodor, Imola and Marson, Enrico and Pellegrino, Felice Andrea and Pin, Gilberto and Salvato, Erica and Toppano, Michele and Zorzenon, Davide",
booktitle = "Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods",
doi = "10.5220/0008935104250432",
editor = "{De Marsico}, Maria and {Sanniti di Baja}, Gabriella and Fred, Ana",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Babichev et al. - 2020 - Loads Estimation using Deep Learning Techniques in Consumer Washing Machines.pdf:pdf",
isbn = "978-989-758-397-1",
month = "feb",
pages = "425--432",
publisher = "SCITEPRESS - Science and Technology Publications",
title = "{Loads Estimation using Deep Learning Techniques in Consumer Washing Machines}",
url = "http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0008935104250432",
year = 2020
}
Niky Bruchon, Gianfranco Fenu, Giulio Gaio, Marco Lonza, Felice Andrea Pellegrino and Erica Salvato.
Toward the Application of Reinforcement Learning to the Intensity Control of a Seeded Free-Electron Laser.
In Adolfo Senatore and Truong Q Dinh (eds.). 2019 23rd International Conference on Mechatronics Technology (ICMT). October 2019, 1–6.
Abstract The optimization of particle accelerators is a challenging task, and many different approaches have been proposed in years, to obtain an optimal tuning of the plant and to keep it optimally tuned despite drifts or disturbances. Indeed, the classical model-free approaches (such as Gradient Ascent or Extremum Seeking algorithms) have intrinsic limitations. To overcome those limitations, Machine Learning techniques, in particular, the Reinforcement Learning, are attracting more and more attention in the particle accelerator community. The purpose of this paper is to apply a Reinforcement Learning model-free approach to the alignment of a seed laser, based on a rather general target function depending on the laser trajectory. The study focuses on the alignment of the lasers at FERMI, the free-electron laser facility at Elettra Sincrotrone Trieste. In particular, we employ Q-learning with linear function approximation and report experimental results obtained in two setups, which are the actual setups where the final application has to be deployed. Despite the simplicity of the approach, we report satisfactory preliminary results, that represent the first step toward a fully automatic procedure for seed laser to the electron beam. Such a superimposition is, at present, performed manually. DOI BibTeX
@inproceedings{bruchon2019toward,
abstract = "The optimization of particle accelerators is a challenging task, and many different approaches have been proposed in years, to obtain an optimal tuning of the plant and to keep it optimally tuned despite drifts or disturbances. Indeed, the classical model-free approaches (such as Gradient Ascent or Extremum Seeking algorithms) have intrinsic limitations. To overcome those limitations, Machine Learning techniques, in particular, the Reinforcement Learning, are attracting more and more attention in the particle accelerator community. The purpose of this paper is to apply a Reinforcement Learning model-free approach to the alignment of a seed laser, based on a rather general target function depending on the laser trajectory. The study focuses on the alignment of the lasers at FERMI, the free-electron laser facility at Elettra Sincrotrone Trieste. In particular, we employ Q-learning with linear function approximation and report experimental results obtained in two setups, which are the actual setups where the final application has to be deployed. Despite the simplicity of the approach, we report satisfactory preliminary results, that represent the first step toward a fully automatic procedure for seed laser to the electron beam. Such a superimposition is, at present, performed manually.",
address = "Salerno",
author = "Bruchon, Niky and Fenu, Gianfranco and Gaio, Giulio and Lonza, Marco and Pellegrino, Felice Andrea and Salvato, Erica",
booktitle = "2019 23rd International Conference on Mechatronics Technology (ICMT)",
doi = "10.1109/ICMECT.2019.8932150",
editor = "Senatore, Adolfo and Dinh, Truong Q.",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Bruchon et al. - 2019 - Toward the Application of Reinforcement Learning to the Intensity Control of a Seeded Free-Electron Laser.pdf:pdf",
issn = "null",
month = "oct",
pages = "1--6",
publisher = "IEEE",
title = "{Toward the Application of Reinforcement Learning to the Intensity Control of a Seeded Free-Electron Laser}",
year = 2019
}
Antonio Acernese, Carmen Del Vecchio, Gianfranco Fenu, Luigi Glielmo and Felice Andrea Pellegrino.
A Combined Support Vector Machine and Support Vector Representation Machine Method for Production Control.
In 2019 18th European Control Conference (ECC). June 2019, 512–517.
Abstract Machine learning techniques have been widely applied to production processes with the aim of improving product quality, supporting decision-making, or implementing process diagnostics. These techniques proved particularly useful in manufacturing industry where huge variety of heterogeneous data, related to different production processes, can be gathered and recorded but where traditional models fail due to the complexity of the production process. In this study, we describe a novel Machine Learning methodology to associate some product attributes (either defects or desirable qualities) to process parameters. Namely we combined Support Vector Ma- chine (SVM) and the Support Vector Representation Machine (SVRM) for instance ranking. The combination of SVM and SVRM guarantees a high flexibility in modeling the decision surfaces (thanks to the kernels) while containing overfitting (thanks to the principle of margin maximization). Thus this method is well suited for modeling unknown, possibly complex relationships, that may not be captured by simple handcrafted models. We applied our method to production data of an investment casting industry placed in South Italy. We obtain an instance ranking that may be used to infer proper values of process parameter set-points. URL, DOI BibTeX
@inproceedings{Acernese2019,
abstract = "Machine learning techniques have been widely applied to production processes with the aim of improving product quality, supporting decision-making, or implementing process diagnostics. These techniques proved particularly useful in manufacturing industry where huge variety of heterogeneous data, related to different production processes, can be gathered and recorded but where traditional models fail due to the complexity of the production process. In this study, we describe a novel Machine Learning methodology to associate some product attributes (either defects or desirable qualities) to process parameters. Namely we combined Support Vector Ma- chine (SVM) and the Support Vector Representation Machine (SVRM) for instance ranking. The combination of SVM and SVRM guarantees a high flexibility in modeling the decision surfaces (thanks to the kernels) while containing overfitting (thanks to the principle of margin maximization). Thus this method is well suited for modeling unknown, possibly complex relationships, that may not be captured by simple handcrafted models. We applied our method to production data of an investment casting industry placed in South Italy. We obtain an instance ranking that may be used to infer proper values of process parameter set-points.",
address = "Naples",
author = "Acernese, Antonio and {Del Vecchio}, Carmen and Fenu, Gianfranco and Glielmo, Luigi and Pellegrino, Felice Andrea",
booktitle = "2019 18th European Control Conference (ECC)",
doi = "10.23919/ECC.2019.8796111",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Acernese et al. - 2019 - A Combined Support Vector Machine and Support Vector Representation Machine Method for Production Control.pdf:pdf",
isbn = 9783907144008,
month = "jun",
pages = "512--517",
publisher = "EUCA",
title = "{A Combined Support Vector Machine and Support Vector Representation Machine Method for Production Control}",
url = "https://ieeexplore.ieee.org/document/8796111",
year = 2019
}
Francesca Cairoli, Gianfranco Fenu, Felice Andrea Pellegrino and Erica Salvato.
Model Predictive Control of glucose concentration based on Signal Temporal Logic specifications.
In 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT). April 2019, 714–719.
Abstract Insulin is a peptide hormone produced by the pancreas to regulate the cells intake of glucose in the blood. Type 1 diabetes compromises this particular capacity of the pancreas. Patients with this disease inject insulin to regulate the level of glucose in the blood, thus reducing the risk of longterm complications. Artificial Pancreas (AP) is a wearable device developed to provide automatic delivery of insuline, allowing a potentially significant improvement in the quality of life of patients. In this paper we apply to the AP a Model Predictive Controller able to generate state trajectories that meet constraints expressed through Signal Temporal Logic (STL). Such a form of constraints is indeed appropriate for the AP, in which some requirements result in hard constraints (absolutely avoid hypoglycaemia) and some other in soft constraints (avoid a prolonged hyperglycaemia). We rely on the BluSTL toolbox, which allows to automatically generate controllers using STL specifications. We perform simulations on two different scenarios: an MPC controller that uses the same constraints as [1] and an MPC-STL controller in both deterministic and adversarial environment (robust control). We show that the soft constraints permitted by STL avoid unnecessary restriction, providing safe trajectories in correspondence of higher disturbance. URL, DOI BibTeX
@inproceedings{Cairoli2019,
abstract = "Insulin is a peptide hormone produced by the pancreas to regulate the cells intake of glucose in the blood. Type 1 diabetes compromises this particular capacity of the pancreas. Patients with this disease inject insulin to regulate the level of glucose in the blood, thus reducing the risk of longterm complications. Artificial Pancreas (AP) is a wearable device developed to provide automatic delivery of insuline, allowing a potentially significant improvement in the quality of life of patients. In this paper we apply to the AP a Model Predictive Controller able to generate state trajectories that meet constraints expressed through Signal Temporal Logic (STL). Such a form of constraints is indeed appropriate for the AP, in which some requirements result in hard constraints (absolutely avoid hypoglycaemia) and some other in soft constraints (avoid a prolonged hyperglycaemia). We rely on the BluSTL toolbox, which allows to automatically generate controllers using STL specifications. We perform simulations on two different scenarios: an MPC controller that uses the same constraints as [1] and an MPC-STL controller in both deterministic and adversarial environment (robust control). We show that the soft constraints permitted by STL avoid unnecessary restriction, providing safe trajectories in correspondence of higher disturbance.",
address = "Paris",
author = "Cairoli, Francesca and Fenu, Gianfranco and Pellegrino, Felice Andrea and Salvato, Erica",
booktitle = "2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)",
doi = "10.1109/CoDIT.2019.8820492",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Cairoli et al. - 2019 - Model Predictive Control of glucose concentration based on Signal Temporal Logic specifications.pdf:pdf",
isbn = 9781728105215,
month = "apr",
pages = "714--719",
publisher = "IEEE",
title = "{Model Predictive Control of glucose concentration based on Signal Temporal Logic specifications}",
url = "https://ieeexplore.ieee.org/document/8820492",
year = 2019
}
Francesca Cairoli, Gianfranco Fenu and Felice Andrea Pellegrino.
Clinical Decision Support Using Colored Petri Nets: a Case Study on Cancer Infusion Therapy.
In 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT). April 2019, 314–319.
Abstract We consider a drug infusion scenario in which a drug is delivered through an infusion pump to a patient, whose vital parameters are monitored via a bedside monitor. Drug infusion therapies are based on clinical protocols that are drug-specific and very diversified. The burden of their proper application on several patients lies, most of the times, on nursing staff alone. With the aim of making the choices safe and prompt and limiting human errors, we build a system that suggests the proper action based on the protocol and the status of the patient. Given the high variability of protocols, it is important to choose a flexible structure. We choose Hierarchical Colored Petri Nets (HCPN), a mathematical formalism for describing discrete event dynamic systems, which is, in fact, modular, expressive and admits a graphic representation. Cancer infusion therapy is the case study considered, as that clinical scenario is likely to become critical from a staff/patient ratio point of view, since the number of patients is continuously growing. URL, DOI BibTeX
@inproceedings{Cairoli2019a,
abstract = "We consider a drug infusion scenario in which a drug is delivered through an infusion pump to a patient, whose vital parameters are monitored via a bedside monitor. Drug infusion therapies are based on clinical protocols that are drug-specific and very diversified. The burden of their proper application on several patients lies, most of the times, on nursing staff alone. With the aim of making the choices safe and prompt and limiting human errors, we build a system that suggests the proper action based on the protocol and the status of the patient. Given the high variability of protocols, it is important to choose a flexible structure. We choose Hierarchical Colored Petri Nets (HCPN), a mathematical formalism for describing discrete event dynamic systems, which is, in fact, modular, expressive and admits a graphic representation. Cancer infusion therapy is the case study considered, as that clinical scenario is likely to become critical from a staff/patient ratio point of view, since the number of patients is continuously growing.",
address = "Paris",
author = "Cairoli, Francesca and Fenu, Gianfranco and Pellegrino, Felice Andrea",
booktitle = "2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)",
doi = "10.1109/CoDIT.2019.8820456",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Cairoli, Fenu, Pellegrino - 2019 - Clinical Decision Support Using Colored Petri Nets a Case Study on Cancer Infusion Therapy.pdf:pdf",
isbn = 9781728105215,
month = "apr",
pages = "314--319",
publisher = "IEEE",
title = "{Clinical Decision Support Using Colored Petri Nets: a Case Study on Cancer Infusion Therapy}",
url = "https://ieeexplore.ieee.org/document/8820456",
year = 2019
}
Marco De Marco, Gianfranco Fenu, Eric Medvet and Felice Andrea Pellegrino.
Computer Vision for the Blind: A Comparison of Face Detectors in a Relevant Scenario.
In Ombretta Gaggi, Pietro Manzoni, Claudio Palazzi, Armir Bujari and Johann M Marquez-Barja (eds.). Smart Objects and Technologies for Social Good: Second International Conference, GOODTECHS 2016, Venice, Italy, November 30 – December 1, 2016, Proceedings. 2017, 145–154.
Abstract Motivated by the aim of developing a vision-based system to assist the social interaction of blind persons, the performance of some face detectors are evaluated. The detectors are applied to manually annotated video sequences acquired by blind persons with a glass-mounted camera and a necklace-mounted one. The sequences are relevant to the specific application and demonstrate to be challenging for all the considered detectors. A further analysis is performed to reveal how the performance is affected by some features such as occlusion, rotations, size and position of the face within the frame. URL, DOI BibTeX
@inproceedings{DeMarco2017,
abstract = "Motivated by the aim of developing a vision-based system to assist the social interaction of blind persons, the performance of some face detectors are evaluated. The detectors are applied to manually annotated video sequences acquired by blind persons with a glass-mounted camera and a necklace-mounted one. The sequences are relevant to the specific application and demonstrate to be challenging for all the considered detectors. A further analysis is performed to reveal how the performance is affected by some features such as occlusion, rotations, size and position of the face within the frame.",
address = "Venice",
author = "{De Marco}, Marco and Fenu, Gianfranco and Medvet, Eric and Pellegrino, Felice Andrea",
booktitle = "Smart Objects and Technologies for Social Good: Second International Conference, GOODTECHS 2016, Venice, Italy, November 30 -- December 1, 2016, Proceedings",
doi = "10.1007/978-3-319-61949-1_16",
editor = "Gaggi, Ombretta and Manzoni, Pietro and Palazzi, Claudio and Bujari, Armir and Marquez-Barja, Johann M",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/De Marco et al. - 2017 - Computer Vision for the Blind A Comparison of Face Detectors in a Relevant Scenario.pdf:pdf",
isbn = "978-3-319-61949-1",
pages = "145--154",
publisher = "Springer International Publishing",
series = "Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering",
title = "{Computer Vision for the Blind: A Comparison of Face Detectors in a Relevant Scenario}",
url = "http://dx.doi.org/10.1007/978-3-319-61949-1_16",
year = 2017
}
Alberto Bartoli, Gianfranco Fenu, Eric Medvet, Felice Andrea Pellegrino and Nicola Timeus.
Segmentation of Mosaic Images Based on Deformable Models Using Genetic Algorithms.
In Ombretta Gaggi, Pietro Manzoni, Claudio Palazzi, Armir Bujari and Johann M Marquez-Barja (eds.). Smart Objects and Technologies for Social Good: Second International Conference, GOODTECHS 2016 Proceedings. 2017, 233–242.
Abstract Preservation and restoration of ancient mosaics is a crucial activity for the perpetuation of cultural heritage of many countries. Such an activity is usually based on manual procedures which are typically lengthy and costly. Digital imaging technologies have a great potential in this important application domain, from a number of points of view including smaller costs and much broader functionalities. In this work, we propose a mosaic-oriented image segmentation algorithm aimed at identifying automatically the tiles composing a mosaic based solely on an image of the mosaic itself. Our proposal consists of a Genetic Algorithm, in which we represent each candidate segmentation with a set of quadrangles whose shapes and positions are modified during an evolutionary search based on multi-objective optimization. We evaluate our proposal in detail on a set of real mosaics which differ in age and style. The results are highly promising and in line with the current state-of-the-art. URL, DOI BibTeX
@inproceedings{Bartoli2017,
abstract = "Preservation and restoration of ancient mosaics is a crucial activity for the perpetuation of cultural heritage of many countries. Such an activity is usually based on manual procedures which are typically lengthy and costly. Digital imaging technologies have a great potential in this important application domain, from a number of points of view including smaller costs and much broader functionalities. In this work, we propose a mosaic-oriented image segmentation algorithm aimed at identifying automatically the tiles composing a mosaic based solely on an image of the mosaic itself. Our proposal consists of a Genetic Algorithm, in which we represent each candidate segmentation with a set of quadrangles whose shapes and positions are modified during an evolutionary search based on multi-objective optimization. We evaluate our proposal in detail on a set of real mosaics which differ in age and style. The results are highly promising and in line with the current state-of-the-art.",
address = "Venice",
author = "Bartoli, Alberto and Fenu, Gianfranco and Medvet, Eric and Pellegrino, Felice Andrea and Timeus, Nicola",
booktitle = "Smart Objects and Technologies for Social Good: Second International Conference, GOODTECHS 2016 Proceedings",
doi = "10.1007/978-3-319-61949-1_25",
editor = "Gaggi, Ombretta and Manzoni, Pietro and Palazzi, Claudio and Bujari, Armir and Marquez-Barja, Johann M",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Bartoli et al. - 2017 - Segmentation of Mosaic Images Based on Deformable Models Using Genetic Algorithms.pdf:pdf",
isbn = "978-3-319-61949-1",
pages = "233--242",
publisher = "Springer International Publishing",
series = "Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering",
title = "{Segmentation of Mosaic Images Based on Deformable Models Using Genetic Algorithms}",
url = "http://dx.doi.org/10.1007/978-3-319-61949-1_25",
year = 2017
}
Franco Blanchini, Gianfranco Fenu, Giulia Giordano and Felice Andrea Pellegrino.
Discrete-Time Trials for Tuning without a Model.
In Proceedings of the 20th IFAC World Congress 50(1). 2017, 1539–1544.
Abstract Given a static plant described by a differentiable input-output function, which is completely unknown, but whose Jacobian takes values in a known polytope in the matrix space, we consider the problem of tuning the output (i.e., driving the output to a desired value), by suitably choosing the input. To this aim, we assume to have at our disposal a discrete sequence of trials only, as it happens, for instance, when we iteratively run a software, with new input data at each iteration, in order to achieve the desired output value. In this paper we prove that, if the polytope is robustly non-singular (or has full row rank, in the general non-square case), then a suitable discrete-time tuning law drives the output to the desired point. The computation of the tuning law is based on a convex-optimisation problem to be solved on-line. An application example is proposed to show the effectiveness of the approach. URL, DOI BibTeX
@inproceedings{Blanchini2017,
abstract = "Given a static plant described by a differentiable input-output function, which is completely unknown, but whose Jacobian takes values in a known polytope in the matrix space, we consider the problem of tuning the output (i.e., driving the output to a desired value), by suitably choosing the input. To this aim, we assume to have at our disposal a discrete sequence of trials only, as it happens, for instance, when we iteratively run a software, with new input data at each iteration, in order to achieve the desired output value. In this paper we prove that, if the polytope is robustly non-singular (or has full row rank, in the general non-square case), then a suitable discrete-time tuning law drives the output to the desired point. The computation of the tuning law is based on a convex-optimisation problem to be solved on-line. An application example is proposed to show the effectiveness of the approach.",
address = "Toulouse",
author = "Blanchini, Franco and Fenu, Gianfranco and Giordano, Giulia and Pellegrino, Felice Andrea",
booktitle = "Proceedings of the 20th IFAC World Congress",
doi = "10.1016/j.ifacol.2017.08.306",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini et al. - 2017 - Discrete-Time Trials for Tuning without a Model.pdf:pdf",
issn = 24058963,
keywords = "Tuning,discrete-time,model-free,plant-tuning,tuning",
number = 1,
pages = "1539--1544",
publisher = "Elsevier B.V.",
title = "{Discrete-Time Trials for Tuning without a Model}",
url = "http://linkinghub.elsevier.com/retrieve/pii/S2405896317306286",
volume = 50,
year = 2017
}
Franco Blanchini, Gianfranco Fenu, Giulia Giordano and Felice Andrea Pellegrino.
Model-free tuning of plants with parasitic dynamics.
In 2017 56th IEEE Conference on Decision and Control (CDC). 2017, 499–504.
Abstract We have recently considered the problem of tun- ing a static plant described by a differentiable input-output function, which is completely unknown, but whose Jacobian takes values in a known polytope of matrices: to drive the output to a given desired value, we have suggested an integral feedback scheme, whose convergence is ensured if the polytope of matrices is robustly full row rank. The suggested tuning scheme may fail in the presence of parasitic dynamics, which may destabilize the loop if the tuning action is too aggressive. Here we show that such tuning action can be applied to dynamic plants as well if it is sufficiently “slow”, a property that we can ensure by limiting the integral action. We provide robust bounds based on the exclusive knowledge of the largest time constant and of the matrix polytope to which the system Jacobian is known to belong. We also provide similar bounds in the presence of parasitic dynamics affecting the actuators. URL, DOI BibTeX
@inproceedings{Blanchini2017cdc,
abstract = "We have recently considered the problem of tun- ing a static plant described by a differentiable input-output function, which is completely unknown, but whose Jacobian takes values in a known polytope of matrices: to drive the output to a given desired value, we have suggested an integral feedback scheme, whose convergence is ensured if the polytope of matrices is robustly full row rank. The suggested tuning scheme may fail in the presence of parasitic dynamics, which may destabilize the loop if the tuning action is too aggressive. Here we show that such tuning action can be applied to dynamic plants as well if it is sufficiently “slow”, a property that we can ensure by limiting the integral action. We provide robust bounds based on the exclusive knowledge of the largest time constant and of the matrix polytope to which the system Jacobian is known to belong. We also provide similar bounds in the presence of parasitic dynamics affecting the actuators.",
address = "Melbourne",
author = "Blanchini, Franco and Fenu, Gianfranco and Giordano, Giulia and Pellegrino, Felice Andrea",
booktitle = "2017 56th IEEE Conference on Decision and Control (CDC)",
doi = "10.1109/CDC.2017.8263713",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini et al. - 2017 - Model-free tuning of plants with parasitic dynamics.pdf:pdf",
isbn = 9781509028726,
keywords = "Lyapunov methods,Robust control,Uncertain systems",
pages = "499--504",
publisher = "IEEE",
title = "{Model-free tuning of plants with parasitic dynamics}",
url = "http://ieeexplore.ieee.org/document/8263713/",
year = 2017
}
Sergio Carrato, Stefano Marsi, Eric Medvet, Felice Andrea Pellegrino, Giovanni Ramponi and Michele Vittori.
Computer Vision for the blind: a dataset for experiments on face detection and recognition.
In Proceedings of the 39th International Convention on Information and Communication Technology, Electronics and Microelectronics. 2016, 1479–1484.
Abstract We present a video dataset created for the needs of a research project that aims at developing vision-based techniques that assist the social interaction of a blind person. Two totally blind users have acquired the sequences, using at the same time a glasses-mounted camera and a necklace-mounted one. The video sequences were acquired in different environments, selecting conditions in which a user could be interested in detecting the presence of some of his/her acquaintances, to approach them in a most natural way. The sequences have been temporally cropped to extract video shots that, by inspection, were deemed to contain events valuable for the goals of the project. The shots are presently being annotated, and some preliminary experiments on face detection have been performed on the annotated data. We also present some observations about the specific application that is being considered. URL, DOI BibTeX
@inproceedings{MIPRO2016,
abstract = "We present a video dataset created for the needs of a research project that aims at developing vision-based techniques that assist the social interaction of a blind person. Two totally blind users have acquired the sequences, using at the same time a glasses-mounted camera and a necklace-mounted one. The video sequences were acquired in different environments, selecting conditions in which a user could be interested in detecting the presence of some of his/her acquaintances, to approach them in a most natural way. The sequences have been temporally cropped to extract video shots that, by inspection, were deemed to contain events valuable for the goals of the project. The shots are presently being annotated, and some preliminary experiments on face detection have been performed on the annotated data. We also present some observations about the specific application that is being considered.",
address = "Opatija",
author = "Carrato, Sergio and Marsi, Stefano and Medvet, Eric and Pellegrino, Felice Andrea and Ramponi, Giovanni and Vittori, Michele",
booktitle = "Proceedings of the 39th International Convention on Information and Communication Technology, Electronics and Microelectronics",
doi = "10.1109/MIPRO.2016.7522323",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Carrato et al. - 2016 - Computer Vision for the blind a dataset for experiments on face detection and recognition(2).pdf:pdf",
pages = "1479--1484",
publisher = "Mipro Croatian Society",
title = "{Computer Vision for the blind: a dataset for experiments on face detection and recognition}",
url = "http://ieeexplore.ieee.org/document/7522323/",
year = 2016
}
Franco Blanchini, Gianfranco Fenu, Giulia Giordano and Felice Andrea Pellegrino.
Inverse kinematics by means of convex programming: some developments.
In Proceedings of the 11th IEEE International Conference on Automation Science and Engineering (CASE 2015). 2015, 515–520.
Abstract A novel approach to the problem of inverse kinematics for redundant manipulators has been recently introduced: by considering the joints as point masses in a fictitious gravity field, and by adding proper constraints to take into account the length of the links, the kinematic inversion may be cast as a convex programming problem. Such a problem can be solved in an efficient way and may be easily modified to include constraints due to obstacles. Here we present further developments of the idea. In particular, for the case of planar robots, we show (i) how to impose hard constraints on the joint angles while preserving the convexity of the problem, and (ii) how to add constraints due to objects (for instance, a load carried by the robot) that are rigidly attached to some part of the robot. DOI BibTeX
@inproceedings{BlanchiniCASE2015,
abstract = "A novel approach to the problem of inverse kinematics for redundant manipulators has been recently introduced: by considering the joints as point masses in a fictitious gravity field, and by adding proper constraints to take into account the length of the links, the kinematic inversion may be cast as a convex programming problem. Such a problem can be solved in an efficient way and may be easily modified to include constraints due to obstacles. Here we present further developments of the idea. In particular, for the case of planar robots, we show (i) how to impose hard constraints on the joint angles while preserving the convexity of the problem, and (ii) how to add constraints due to objects (for instance, a load carried by the robot) that are rigidly attached to some part of the robot.",
address = "Gothenburg",
author = "Blanchini, Franco and Fenu, Gianfranco and Giordano, Giulia and Pellegrino, Felice Andrea",
booktitle = "Proceedings of the 11th IEEE International Conference on Automation Science and Engineering (CASE 2015)",
doi = "10.1109/CoASE.2015.7294131",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini et al. - 2015 - Inverse kinematics by means of convex programming some developments.pdf:pdf",
isbn = 9781467381833,
keywords = "Automation for Machine Tools,Mechatronics,Scheduling and Optimization",
pages = "515--520",
title = "{Inverse kinematics by means of convex programming: some developments}",
year = 2015
}
Margherita Bonetto, Sergio Carrato, Gianfranco Fenu, Eric Medvet, Enzo Mumolo, Felice Andrea Pellegrino and Giovanni Ramponi.
Image Processing Issues in a Social Assistive System for the Blind.
In Image and Signal Processing and Analysis (ISPA), 2015 9th International Symposium on. 2015, 216–221.
Abstract We systematically analyse the design of the low- level vision components of a real-time system able to help a blind person in his/her social interactions. We focus on the acquisition and processing of the video sequences that are acquired by a wearable sensor (a smartphone camera or a Webcam) for the detection of faces in the scene. We review some classical and some very recent techniques that seem appropriate to the requirements of our goal. DOI BibTeX
@inproceedings{bonetto2015,
abstract = "We systematically analyse the design of the low- level vision components of a real-time system able to help a blind person in his/her social interactions. We focus on the acquisition and processing of the video sequences that are acquired by a wearable sensor (a smartphone camera or a Webcam) for the detection of faces in the scene. We review some classical and some very recent techniques that seem appropriate to the requirements of our goal.",
address = "Zagreb",
author = "Bonetto, Margherita and Carrato, Sergio and Fenu, Gianfranco and Medvet, Eric and Mumolo, Enzo and Pellegrino, Felice Andrea and Ramponi, Giovanni",
booktitle = "Image and Signal Processing and Analysis (ISPA), 2015 9th International Symposium on",
doi = "10.1109/ISPA.2015.7306061",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Bonetto et al. - 2015 - Image Processing Issues in a Social Assistive System for the Blind.pdf:pdf",
isbn = 9781467380324,
keywords = "Cameras,Distortion,Face detection,Face recognition,Image processing,Lighting,Signal processing algorithms",
pages = "216--221",
title = "{Image Processing Issues in a Social Assistive System for the Blind}",
year = 2015
}
Gianfranco Fenu, Nikita Jain, Eric Medvet, Felice Andrea Pellegrino and Myriam Pilutti Namer.
On the Assessment of Segmentation Methods for Images of Mosaics.
In Proceedings of 10th International Conference on Computer Vision Theory and Applications VISAPP 2015. 2015, 130–137.
Abstract The present paper deals with automatic segmentation of mosaics, whose aim is obtaining a digital representation of the mosaic where the shape of each tile is recovered. This is an important step, for instance, for preserving ancient mosaics. By using a ground-truth consisting of a set of manually annotated mosaics, we objectively compare the performance of some existing recent segmentation methods, based on a simple error metric taking into account precision, recall and the error on the number of tiles. Moreover, we introduce some mosaic-specific hardness estimators (namely some indexes of how difficult is the task of segmenting a particular mosaic image). The results show that the only segmentation algorithm specifically designed for mosaics performs better than the general purpose algorithms. However, the problem of segmentation of mosaics appears still partially unresolved and further work is needed for exploiting the specificity of mosaics in designing new segmentation algorithms. DOI BibTeX
@inproceedings{Fenu2015,
abstract = "The present paper deals with automatic segmentation of mosaics, whose aim is obtaining a digital representation of the mosaic where the shape of each tile is recovered. This is an important step, for instance, for preserving ancient mosaics. By using a ground-truth consisting of a set of manually annotated mosaics, we objectively compare the performance of some existing recent segmentation methods, based on a simple error metric taking into account precision, recall and the error on the number of tiles. Moreover, we introduce some mosaic-specific hardness estimators (namely some indexes of how difficult is the task of segmenting a particular mosaic image). The results show that the only segmentation algorithm specifically designed for mosaics performs better than the general purpose algorithms. However, the problem of segmentation of mosaics appears still partially unresolved and further work is needed for exploiting the specificity of mosaics in designing new segmentation algorithms.",
address = "Berlin",
author = "Fenu, Gianfranco and Jain, Nikita and Medvet, Eric and Pellegrino, Felice Andrea and {Pilutti Namer}, Myriam",
booktitle = "Proceedings of 10th International Conference on Computer Vision Theory and Applications VISAPP 2015",
doi = "10.13140/RG.2.1.3025.6489",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Fenu et al. - 2015 - On the Assessment of Segmentation Methods for Images of Mosaics(2).pdf:pdf",
keywords = "comparative evaluation,cultural heritage preservation,image segmentation,superpixel",
pages = "130--137",
title = "{On the Assessment of Segmentation Methods for Images of Mosaics}",
year = 2015
}
Franco Blanchini, Gianfranco Fenu, Giulia Giordano and Felice Andrea Pellegrino.
Plant tuning: A robust Lyapunov approach.
In Decision and Control (CDC), 2015 IEEE 54th Annual Conference on. 2015, 1142–1147.
Abstract We consider the problem of tuning the output of a static plant whose model is unknown, under the only information that the input–output function is monotonic in each component or, more in general, that its Jacobian belongs to a known polytope of matrices. As a main result, we show that, if the polytope is robustly non–singular (or has full rank, in the non–square case), then a suitable tuning scheme drives the output to a desired point. The proof is based on the application of a well known theorem concerning the existence of a saddle point for a min–max zero–sum game. Some application examples are suggested. DOI BibTeX
@inproceedings{Blanchini2015CDC,
abstract = "We consider the problem of tuning the output of a static plant whose model is unknown, under the only information that the input–output function is monotonic in each component or, more in general, that its Jacobian belongs to a known polytope of matrices. As a main result, we show that, if the polytope is robustly non–singular (or has full rank, in the non–square case), then a suitable tuning scheme drives the output to a desired point. The proof is based on the application of a well known theorem concerning the existence of a saddle point for a min–max zero–sum game. Some application examples are suggested.",
address = "Osaka",
author = "Blanchini, Franco and Fenu, Gianfranco and Giordano, Giulia and Pellegrino, Felice Andrea",
booktitle = "Decision and Control (CDC), 2015 IEEE 54th Annual Conference on",
doi = "10.1109/CDC.2015.7402365",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini et al. - 2015 - Plant tuning A robust Lyapunov approach.pdf:pdf",
keywords = "Games,Heating,Humidity,Jacobian matrices,Market research,Robustness,Tuning",
pages = "1142--1147",
publisher = "IEEE",
title = "{Plant tuning: A robust Lyapunov approach}",
year = 2015
}
Daniele Tognetto, Silvia Rinaldi, Claudia Papagno, Gianfranco Fenu, Felice Andrea Pellegrino and Paolo Sirotti.
Quality of Images With Premium IOLs.
In ASCRS Symposium on Cataract, IOL and Refractive Surgery. 2013.
Abstract To evaluate the quality of images obtained with different type of premium intraocular lenses (IOLs) by developing an optoelectronic test bench including an artificial eye. An experimental opto-electronic test bench has been realized following the Gullstrand eye model and ISO 11979-2 norm. The system includes an electro-opto-mechanical device that simulates the optical and geometric characteristics of the human eye. The PMMA artificial cornea has been realized with optical and geometric properties similar to those of a real cornea. A cylindrical lens is placed in front of the artificial cornea to simulate corneal astigmatism. Toric IOL were analized evaluating the Modulation Transfer Function (MTF) and the quality of different images. A relevant software was realized to capture, store images and evaluate their quality in accordance with established criteria. Images transmitted through an astigmatic cornea are corrected by the toric IOL as much as the axis of the lens correspond to the axis of the astigmatism thus improving the transmission of different spatial frequencies and the quality of test images. Pupil diameter affects the quality of images especially when a residual refractive error is induced. This opto-electronic test bench allows to determine the quality of images transmitted by premium intraocular lenses in different refractive and optical conditions. Toric IOL have been studied demonstrating their ability to correct the corneal astigmatism. This system allows to evaluate different criteria besides the MTF, such as the evaluation of sharpness or the distortion of local image patterns or even to formulate new objective image evaluating criteria. BibTeX
@inproceedings{tognetto2012,
abstract = "To evaluate the quality of images obtained with different type of premium intraocular lenses (IOLs) by developing an optoelectronic test bench including an artificial eye. An experimental opto-electronic test bench has been realized following the Gullstrand eye model and ISO 11979-2 norm. The system includes an electro-opto-mechanical device that simulates the optical and geometric characteristics of the human eye. The PMMA artificial cornea has been realized with optical and geometric properties similar to those of a real cornea. A cylindrical lens is placed in front of the artificial cornea to simulate corneal astigmatism. Toric IOL were analized evaluating the Modulation Transfer Function (MTF) and the quality of different images. A relevant software was realized to capture, store images and evaluate their quality in accordance with established criteria. Images transmitted through an astigmatic cornea are corrected by the toric IOL as much as the axis of the lens correspond to the axis of the astigmatism thus improving the transmission of different spatial frequencies and the quality of test images. Pupil diameter affects the quality of images especially when a residual refractive error is induced. This opto-electronic test bench allows to determine the quality of images transmitted by premium intraocular lenses in different refractive and optical conditions. Toric IOL have been studied demonstrating their ability to correct the corneal astigmatism. This system allows to evaluate different criteria besides the MTF, such as the evaluation of sharpness or the distortion of local image patterns or even to formulate new objective image evaluating criteria.",
address = "Chicago",
author = "Tognetto, Daniele and Rinaldi, Silvia and Papagno, Claudia and Fenu, Gianfranco and Pellegrino, Felice Andrea and Sirotti, Paolo",
booktitle = "ASCRS Symposium on Cataract, IOL and Refractive Surgery",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Tognetto et al. - 2013 - Quality of Images With Premium IOLs.pdf:pdf",
title = "{Quality of Images With Premium IOLs}",
year = 2013
}
Daniele Tognetto, Silvia Rinaldi, Claudia Papagno, Gianfranco Fenu, Felice Andrea Pellegrino and Paolo Sirotti.
Quality of Images with Multifocal IOLs.
In ASCRS-ASOA Symposium & Congress. 2013. BibTeX
@inproceedings{tognetto2013,
address = "San Francisco",
author = "Tognetto, Daniele and Rinaldi, Silvia and Papagno, Claudia and Fenu, Gianfranco and Pellegrino, Felice Andrea and Sirotti, Paolo",
booktitle = "ASCRS-ASOA Symposium & Congress",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Tognetto et al. - 2013 - Quality of Images with Multifocal IOLs.pdf:pdf",
title = "{Quality of Images with Multifocal IOLs}",
year = 2013
}
Daniele Casagrande, Gianfranco Fenu, Felice Andrea Pellegrino and Alessandro Astolfi.
Application of Hamiltonian dynamics to manipulator control in constrained workspace.
In Proceedings of the 52nd IEEE Conference on Decision and Control. 2013, 1634–1639.
Abstract We describe a methodology to plan the trajectory of a robotic manipulator moving in an n-dimensional Euclidean space. The robot has to reach a target avoiding obstacles and is allowed to move in a constrained space. We show that if the position of the target and of the obstacles in known a priori, then a Hamiltonian function can be constructed and used to define the trajectory. A simulation concerning a real three-dimensional manipulator is finally reported. DOI BibTeX
@inproceedings{Casagrande2013,
abstract = "We describe a methodology to plan the trajectory of a robotic manipulator moving in an n-dimensional Euclidean space. The robot has to reach a target avoiding obstacles and is allowed to move in a constrained space. We show that if the position of the target and of the obstacles in known a priori, then a Hamiltonian function can be constructed and used to define the trajectory. A simulation concerning a real three-dimensional manipulator is finally reported.",
address = "Florence",
author = "Casagrande, Daniele and Fenu, Gianfranco and Pellegrino, Felice Andrea and Astolfi, Alessandro",
booktitle = "Proceedings of the 52nd IEEE Conference on Decision and Control",
doi = "10.1109/CDC.2013.6760116",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Casagrande et al. - 2013 - Application of Hamiltonian dynamics to manipulator control in constrained workspace.pdf:pdf",
pages = "1634--1639",
title = "{Application of Hamiltonian dynamics to manipulator control in constrained workspace}",
year = 2013
}
Andrea Cigaina, Gianfranco Fenu, Felice Andrea Pellegrino, Paolo Sirotti, Silvia Rinaldi and Daniele Tognetto.
Experimental setup and methodology for automatic quality assessment of intraocular lenses.
In Image and Signal Processing and Analysis (ISPA), 2013 8th International Symposium on. 2013, 677–682.
Abstract Intraocular lenses (IOLs) are widely used in cataract surgery. There is a variety of IOLs depending on lens material, optical and mechanical design. Evaluation of the visual performance obtainable with intraocular lenses is important for objective comparison between IOL models. Indeed, the visual performance of implanted lenses has a deep impact on the life of the subjects, having medical, social and economical consequences. The purpose of the present paper is twofold: first, we propose an experimental setup, consisting of an actuated opto–electro– mechanical eye capable of simulating different refractive and optical conditions. Second, we suggest to employ some well– known image quality assessment tools for evaluating the visual performance of different IOLs (or of the same IOL in different conditions) based on the comparison between the original image and that produced by the artificial eye equipped with the IOL. The objective and repeatable results obtained, are in accor- dance with subjective evaluation (a time–consuming procedure employed in previous works). DOI BibTeX
@inproceedings{Cigaina2013,
abstract = "Intraocular lenses (IOLs) are widely used in cataract surgery. There is a variety of IOLs depending on lens material, optical and mechanical design. Evaluation of the visual performance obtainable with intraocular lenses is important for objective comparison between IOL models. Indeed, the visual performance of implanted lenses has a deep impact on the life of the subjects, having medical, social and economical consequences. The purpose of the present paper is twofold: first, we propose an experimental setup, consisting of an actuated opto–electro– mechanical eye capable of simulating different refractive and optical conditions. Second, we suggest to employ some well– known image quality assessment tools for evaluating the visual performance of different IOLs (or of the same IOL in different conditions) based on the comparison between the original image and that produced by the artificial eye equipped with the IOL. The objective and repeatable results obtained, are in accor- dance with subjective evaluation (a time–consuming procedure employed in previous works).",
address = "Trieste",
author = "Cigaina, Andrea and Fenu, Gianfranco and Pellegrino, Felice Andrea and Sirotti, Paolo and Rinaldi, Silvia and Tognetto, Daniele",
booktitle = "Image and Signal Processing and Analysis (ISPA), 2013 8th International Symposium on",
doi = "10.1109/ISPA.2013.6703824",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Cigaina et al. - 2013 - Experimental setup and methodology for automatic quality assessment of intraocular lenses.pdf:pdf",
pages = "677--682",
title = "{Experimental setup and methodology for automatic quality assessment of intraocular lenses}",
year = 2013
}
Paolo Fabris, Walter Vanzella and Felice Andrea Pellegrino.
Evaluation of features for automatic detection of cell nuclei in fluorescence microscopy images.
In Image and Signal Processing and Analysis (ISPA), 2013 8th International Symposium on. 2013, 683–688.
Abstract The problem of detecting cell nuclei in images may be faced by means of a segmentation the neighbourhood of candidate nuclei, followed by a binary classification step. Important for the latter step is the choice of the descriptors (features) to be extracted from the neighbourhood and used by the classifier. In the present paper, based on a large set of manually labelled samples, we evaluate several of such descriptors combined with some common type of support vector machines. We show that equipping the detection algorithm with the best combination of features/classifier leads to a performance comparable to human labelling by experts. DOI BibTeX
@inproceedings{Fabris2013,
abstract = "The problem of detecting cell nuclei in images may be faced by means of a segmentation the neighbourhood of candidate nuclei, followed by a binary classification step. Important for the latter step is the choice of the descriptors (features) to be extracted from the neighbourhood and used by the classifier. In the present paper, based on a large set of manually labelled samples, we evaluate several of such descriptors combined with some common type of support vector machines. We show that equipping the detection algorithm with the best combination of features/classifier leads to a performance comparable to human labelling by experts.",
address = "Trieste",
author = "Fabris, Paolo and Vanzella, Walter and Pellegrino, Felice Andrea",
booktitle = "Image and Signal Processing and Analysis (ISPA), 2013 8th International Symposium on",
doi = "10.1109/ISPA.2013.6703825",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Fabris, Vanzella, Pellegrino - 2013 - Evaluation of features for automatic detection of cell nuclei in fluorescence microscopy images.pdf:pdf",
pages = "683--688",
title = "{Evaluation of features for automatic detection of cell nuclei in fluorescence microscopy images}",
year = 2013
}
Lorenzo Dal Col and Felice Andrea Pellegrino.
Fast and Accurate Object Detection by Means of Recursive Monomial Feature Elimination and Cascade of SVM.
In M P Fanti and A Giua (eds.). Proceedings of the IEEE Conference on Automation Science and Engineering, Trieste, Italy. 2011, 304–309.
Abstract Support Vector Machines (SVMs) are an established tool for pattern recognition. However, their application to real–time object detection (such as detection of objects in each frame of a video stream) is limited due to the relatively high computational cost. Speed is indeed crucial in such applications. Motivated by a practical problem (hand detection), we show how second–degree polynomial SVMs in their primal formulation, along with a recursive elimination of monomial features and a cascade architecture can lead to a fast and accurate classifier. For the considered hand detection problem we obtain a speed–up factor of 1600 with comparable classification performance with respect to a single, unreduced SVM. DOI BibTeX
@inproceedings{DalCol2011,
abstract = "Support Vector Machines (SVMs) are an established tool for pattern recognition. However, their application to real–time object detection (such as detection of objects in each frame of a video stream) is limited due to the relatively high computational cost. Speed is indeed crucial in such applications. Motivated by a practical problem (hand detection), we show how second–degree polynomial SVMs in their primal formulation, along with a recursive elimination of monomial features and a cascade architecture can lead to a fast and accurate classifier. For the considered hand detection problem we obtain a speed–up factor of 1600 with comparable classification performance with respect to a single, unreduced SVM.",
address = "Trieste",
author = "{Dal Col}, Lorenzo and Pellegrino, Felice Andrea",
booktitle = "Proceedings of the IEEE Conference on Automation Science and Engineering, Trieste, Italy",
doi = "10.1109/CASE.2011.6042464",
editor = "Fanti, M.P. and Giua, A.",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Dal Col, Pellegrino - 2011 - Fast and Accurate Object Detection by Means of Recursive Monomial Feature Elimination and Cascade of SVM.pdf:pdf",
keywords = "SVM,feature selection,hand detection,object detection",
pages = "304--309",
title = "{Fast and Accurate Object Detection by Means of Recursive Monomial Feature Elimination and Cascade of SVM}",
year = 2011
}
Francesca Boem, Felice Andrea Pellegrino, Gianfranco Fenu and Thomas Parisini.
Multi-feature trajectory clustering using Earth Mover's Distance.
In Proceedings of the IEEE Conference on Automation Science and Engineering, Trieste, Italy. 2011, 310–315.
Abstract We present new results in trajectory clustering, obtained by extending a recent methodology based on Earth Mover's Distance (EMD). The EMD can be adapted as a tool for trajectory clustering, taking advantage of an effective method for identifying the clusters' representatives by means of the p−median location problem. This methodology can be used either in an unsupervised fashion, or on-line, classifying new trajectories or part of them; it is able to manage different length and noisy trajectories, occlusions and takes velocity profiles and stops into account. We extend our previous work by taking into account other features besides the spatial locations, in particular the direction of movement in correspondence of each trajectory point. We discuss the simulation results and we compare our approach with another trajectory clustering method. DOI BibTeX
@inproceedings{Boem2011,
abstract = "We present new results in trajectory clustering, obtained by extending a recent methodology based on Earth Mover's Distance (EMD). The EMD can be adapted as a tool for trajectory clustering, taking advantage of an effective method for identifying the clusters' representatives by means of the p−median location problem. This methodology can be used either in an unsupervised fashion, or on-line, classifying new trajectories or part of them; it is able to manage different length and noisy trajectories, occlusions and takes velocity profiles and stops into account. We extend our previous work by taking into account other features besides the spatial locations, in particular the direction of movement in correspondence of each trajectory point. We discuss the simulation results and we compare our approach with another trajectory clustering method.",
address = "Trieste",
author = "Boem, Francesca and Pellegrino, Felice Andrea and Fenu, Gianfranco and Parisini, Thomas",
booktitle = "Proceedings of the IEEE Conference on Automation Science and Engineering, Trieste, Italy",
doi = "10.1109/CASE.2011.6042423",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Boem et al. - 2011 - Multi-feature trajectory clustering using Earth Mover's Distance.pdf:pdf",
pages = "310--315",
title = "{Multi-feature trajectory clustering using Earth Mover's Distance}",
year = 2011
}
Francesca Boem, Felice Andrea Pellegrino, Gianfranco Fenu and Thomas Parisini.
Trajectory clustering by means of Earth Mover's Distance.
In Proceedings of IFAC World Congress, Milano, Italy. 2011, 4741–4746.
Abstract We propose a method for trajectory classification based on a general cluster-based methodology, that can be used both off-line in an unsupervised fashion, both on-line, classifying new trajectories or part of them. We use the Earth Mover's Distance (EMD) and we adapt it in order to employ it as a tool for trajectory clustering. We propose a novel effective method to identify the clusters' representatives by means of the p−median location problem. This methodology is able to manage different length and noisy trajectories and takes velocity profiles and stops into account. We discuss the experimental results and we compare our approach with other trajectory clustering methods. DOI BibTeX
@inproceedings{Boem2011b,
abstract = "We propose a method for trajectory classification based on a general cluster-based methodology, that can be used both off-line in an unsupervised fashion, both on-line, classifying new trajectories or part of them. We use the Earth Mover's Distance (EMD) and we adapt it in order to employ it as a tool for trajectory clustering. We propose a novel effective method to identify the clusters' representatives by means of the p−median location problem. This methodology is able to manage different length and noisy trajectories and takes velocity profiles and stops into account. We discuss the experimental results and we compare our approach with other trajectory clustering methods.",
address = "Milan",
author = "Boem, Francesca and Pellegrino, Felice Andrea and Fenu, Gianfranco and Parisini, Thomas",
booktitle = "Proceedings of IFAC World Congress, Milano, Italy",
doi = "10.3182/20110828-6-IT-1002.01230",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Boem et al. - 2011 - Trajectory clustering by means of Earth Mover's Distance.pdf:pdf",
keywords = "Guidance navigation and control,Information and sensor fusion",
pages = "4741--4746",
title = "{Trajectory clustering by means of Earth Mover's Distance}",
year = 2011
}
Daniele Casagrande, Felice Andrea Pellegrino and Alessandro Astolfi.
Hamiltonian dynamics for robot navigation.
In The 9th IEEE International Conference on Control and Automation (ICCA). 2011, 118–123.
Abstract We describe a methodology to plan the trajectory of a robot moving in a two-dimensional space. The robot has to perform the task of reaching a target avoiding obstacles. We show that if the position of the target and of the obstacles in known a priori, then a suitable Hamiltonian function can be constructed and used to define the trajectory. We consider both the static case, namely the case in which both the target and the obstacles are fixed, and the dynamic case, namely the case in which the target or the obstacles move. We prove that in both cases the target can be reached in finite time. The paper is enriched by several examples that accompany the discussion. DOI BibTeX
@inproceedings{Casagrande2011,
abstract = "We describe a methodology to plan the trajectory of a robot moving in a two-dimensional space. The robot has to perform the task of reaching a target avoiding obstacles. We show that if the position of the target and of the obstacles in known a priori, then a suitable Hamiltonian function can be constructed and used to define the trajectory. We consider both the static case, namely the case in which both the target and the obstacles are fixed, and the dynamic case, namely the case in which the target or the obstacles move. We prove that in both cases the target can be reached in finite time. The paper is enriched by several examples that accompany the discussion.",
address = "Santiago",
author = "Casagrande, Daniele and Pellegrino, Felice Andrea and Astolfi, Alessandro",
booktitle = "The 9th IEEE International Conference on Control and Automation (ICCA)",
doi = "10.1109/ICCA.2011.6138023",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Casagrande, Pellegrino, Astolfi - 2011 - Hamiltonian dynamics for robot navigation.pdf:pdf",
pages = "118--123",
title = "{Hamiltonian dynamics for robot navigation}",
year = 2011
}
Gilberto Pin, Marco Filippo, Felice Andrea Pellegrino, Gianfranco Fenu and Thomas Parisini.
Approximate off-line receding horizon control of constrained nonlinear discrete-time systems: Smooth approximation of the control law.
In American Control Conference (ACC), 2010. 2010, 6268–6273.
Abstract In this work, the off-line approximation of state-feedback nonlinear model predictive control laws by means of smooth functions of the state is addressed. The idea is to investigate how the approximation errors affect the stability of the closed-loop system, in order to derive suitable bounds which have to be fulfilled by the approximating function. This analysis allows to conveniently set up the characteristic parameters of some techniques such as Neural Networks which can be used to implement the control law, in order to render the system Input-to-State Practically Stable while satisfying, in addition, hard constraints on the trajectories; both the amount of data storage and the computational time result strongly reduced with respect to Nearest Neighbor or Set Membership approaches, which have been recently proposed to obtain effective off-line approximation of nonlinear MPC. The provided simulations confirm the validity of the method. DOI BibTeX
@inproceedings{PinFilPelFenPar2010,
abstract = "In this work, the off-line approximation of state-feedback nonlinear model predictive control laws by means of smooth functions of the state is addressed. The idea is to investigate how the approximation errors affect the stability of the closed-loop system, in order to derive suitable bounds which have to be fulfilled by the approximating function. This analysis allows to conveniently set up the characteristic parameters of some techniques such as Neural Networks which can be used to implement the control law, in order to render the system Input-to-State Practically Stable while satisfying, in addition, hard constraints on the trajectories; both the amount of data storage and the computational time result strongly reduced with respect to Nearest Neighbor or Set Membership approaches, which have been recently proposed to obtain effective off-line approximation of nonlinear MPC. The provided simulations confirm the validity of the method.",
address = "Baltimore",
author = "Pin, Gilberto and Filippo, Marco and Pellegrino, Felice Andrea and Fenu, Gianfranco and Parisini, Thomas",
booktitle = "American Control Conference (ACC), 2010",
doi = "10.1109/ACC.2010.5531521",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Pin et al. - 2010 - Approximate off-line receding horizon control of constrained nonlinear discrete-time systems Smooth approximation of.pdf:pdf",
isbn = "978-1-4244-7426-4",
issn = "0743-1619",
pages = "6268--6273",
title = "{Approximate off-line receding horizon control of constrained nonlinear discrete-time systems: Smooth approximation of the control law}",
year = 2010
}
Gilberto Pin, Marco Filippo, Felice Andrea Pellegrino and Thomas Parisini.
Approximate off-line receding horizon control of constrained nonlinear discrete-time systems.
In Proc. of the European Control Conference. 2009, 2420–2425.
Abstract The present paper concerns the design of approximate off-line model predictive control laws for nonlinear discrete-time systems subject to hard constraints on state and input variables. The possibility to obtain an approximate receding horizon control law by performing off-line optimization, leads to a dramatic reduction of the real-time computational complexity with respect to on-line algorithms, and allows the application of the developed control technique to plants with fast dynamics, that require small sampling periods. The main feature of the proposed approximation scheme consists in the possibility to cope with possibly discontinuous state-feedback control laws, while guaranteeing the fulfillment of hard constraints on state and input variables despite the perturbations due to the use of an approximate controller. Finally, the resulting closed-loop system is shown to be input-to-state-stable with respect to the approximation-induced perturbations. URL BibTeX
@inproceedings{Pin2009,
abstract = "The present paper concerns the design of approximate off-line model predictive control laws for nonlinear discrete-time systems subject to hard constraints on state and input variables. The possibility to obtain an approximate receding horizon control law by performing off-line optimization, leads to a dramatic reduction of the real-time computational complexity with respect to on-line algorithms, and allows the application of the developed control technique to plants with fast dynamics, that require small sampling periods. The main feature of the proposed approximation scheme consists in the possibility to cope with possibly discontinuous state-feedback control laws, while guaranteeing the fulfillment of hard constraints on state and input variables despite the perturbations due to the use of an approximate controller. Finally, the resulting closed-loop system is shown to be input-to-state-stable with respect to the approximation-induced perturbations.",
address = "Budapest",
author = "Pin, Gilberto and Filippo, Marco and Pellegrino, Felice Andrea and Parisini, Thomas",
booktitle = "Proc. of the European Control Conference",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Pin et al. - 2009 - Approximate off-line receding horizon control of constrained nonlinear discrete-time systems(2).pdf:pdf",
pages = "2420--2425",
title = "{Approximate off-line receding horizon control of constrained nonlinear discrete-time systems}",
url = "http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7074768",
year = 2009
}
Franco Blanchini, Thomas Parisini, Felice Andrea Pellegrino and Gilberto Pin.
High-gain adaptive control: A derivative-based approach.
In Proceedings of the 47th IEEE Conference on Decision and Control. 2008, 3233–3238.
Abstract We propose an adaptive scheme which is a coun- terpart of existing high gain control techniques based on control Lyapunov functions. Given a control Lyapunov function, the main idea is that of tuning the feedback gain according to a suitably–chosen Lyapunov time–derivative. The control gain is not monotonically non–decreasing as in existing techniques, but it is increased or decreased depending on the imposed derivative, thus avoiding the well-known issue of actuator over– exploitation. We are able to show robust convergence of the proposed adaptive control scheme as well as other interesting properties. For instance, it is possible to guarantee an a–priori given upper bound for the transient mode of behavior during adaptation. Furthermore, if the control Lyapunov function is designed based on an optimal control problem, then the control action is nominally optimal, precisely it yields the optimal trajectory for any initial condition, if the actual plant matches the nominal system. DOI BibTeX
@inproceedings{Blanchini2008b,
abstract = "We propose an adaptive scheme which is a coun- terpart of existing high gain control techniques based on control Lyapunov functions. Given a control Lyapunov function, the main idea is that of tuning the feedback gain according to a suitably–chosen Lyapunov time–derivative. The control gain is not monotonically non–decreasing as in existing techniques, but it is increased or decreased depending on the imposed derivative, thus avoiding the well-known issue of actuator over– exploitation. We are able to show robust convergence of the proposed adaptive control scheme as well as other interesting properties. For instance, it is possible to guarantee an a–priori given upper bound for the transient mode of behavior during adaptation. Furthermore, if the control Lyapunov function is designed based on an optimal control problem, then the control action is nominally optimal, precisely it yields the optimal trajectory for any initial condition, if the actual plant matches the nominal system.",
address = "Cancun",
author = "Blanchini, Franco and Parisini, Thomas and Pellegrino, Felice Andrea and Pin, Gilberto",
booktitle = "Proceedings of the 47th IEEE Conference on Decision and Control",
doi = "10.1109/CDC.2008.4739129",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini et al. - 2008 - High-gain adaptive control A derivative-based approach.pdf:pdf",
isbn = "978-1-4244-3123-6",
keywords = "Lyapunov methods,Robust adaptive control,Uncertain systems",
pages = "3233--3238",
title = "{High-gain adaptive control: A derivative-based approach}",
year = 2008
}
Franco Blanchini and Felice Andrea Pellegrino.
Relatively optimal control: a static piecewise-affine solution.
In Proceedings of the 46th IEEE Conference on Decision and Control. 2007, 807–812.
Abstract A relatively optimal control is a stabilizing controller that, without initialization nor feedforwarding and tracking the optimal trajectory, produces the optimal (constrained) behavior for the nominal initial condition of the plant. In a previous work, for discrete–time linear systems, we presented a linear dynamic relatively optimal control. Here we provide a static solution, namely a dead–beat piecewise affine state–feedback controller based on a suitable partition of the state space into polyhedral sets. The vertices of the polyhedra are the states of the optimal trajectory, hence a bound for the complexity of the controller is known in advance. We also show how to obtain a controller that is not dead–beat by removing the zero terminal constraint while guaranteeing stability. DOI BibTeX
@inproceedings{Blanchini2007b,
abstract = "A relatively optimal control is a stabilizing controller that, without initialization nor feedforwarding and tracking the optimal trajectory, produces the optimal (constrained) behavior for the nominal initial condition of the plant. In a previous work, for discrete–time linear systems, we presented a linear dynamic relatively optimal control. Here we provide a static solution, namely a dead–beat piecewise affine state–feedback controller based on a suitable partition of the state space into polyhedral sets. The vertices of the polyhedra are the states of the optimal trajectory, hence a bound for the complexity of the controller is known in advance. We also show how to obtain a controller that is not dead–beat by removing the zero terminal constraint while guaranteeing stability.",
address = "New Orleans",
author = "Blanchini, Franco and Pellegrino, Felice Andrea",
booktitle = "Proceedings of the 46th IEEE Conference on Decision and Control",
doi = "10.1109/CDC.2007.4435045",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini, Pellegrino - 2007 - Relatively optimal control a static piecewise-affine solution.pdf:pdf",
isbn = "978-1-4244-1497-0",
pages = "807--812",
title = "{Relatively optimal control: a static piecewise-affine solution}",
year = 2007
}
Franco Blanchini, Patrizio Colaneri and Felice Andrea Pellegrino.
Compensator blending: a new tool for multiobjective design.
In Proceedings of the 5th IFAC Symposium on Robust Control Design. 2006.
Abstract In this paper we show that (under some input matrix rank conditions) there exists a single compensator which achieves simultaneously the performances of r ≤ n (the system order) given static state feedback (local) compensators. The compensator, whose order is r(n − 1), is then capable of matching the r (possibly different) optimality criteria defined for each input-output pair. An explicit and easy construction procedure (we refer to such procedure as “compensator blending”) is provided. We also consider the dual version of the problem, precisely, we show how to achieve simultaneous optimality by blending a set of given filters. DOI BibTeX
@inproceedings{Blanchini2006,
abstract = "In this paper we show that (under some input matrix rank conditions) there exists a single compensator which achieves simultaneously the performances of r ≤ n (the system order) given static state feedback (local) compensators. The compensator, whose order is r(n − 1), is then capable of matching the r (possibly different) optimality criteria defined for each input-output pair. An explicit and easy construction procedure (we refer to such procedure as “compensator blending”) is provided. We also consider the dual version of the problem, precisely, we show how to achieve simultaneous optimality by blending a set of given filters.",
address = "Toulouse",
author = "Blanchini, Franco and Colaneri, Patrizio and Pellegrino, Felice Andrea",
booktitle = "Proceedings of the 5th IFAC Symposium on Robust Control Design",
doi = "10.3182/20060705-3-FR-2907.00002",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini, Colaneri, Pellegrino - 2006 - Compensator blending a new tool for multiobjective design(2).pdf:pdf",
keywords = "constrained control,mixed-objective control,optimal control",
title = "{Compensator blending: a new tool for multiobjective design}",
year = 2006
}
Franco Blanchini and Felice Andrea Pellegrino.
Relatively Optimal Control: the Static Solution.
In Proceedings of the 16th IFAC World Congress. 2005.
Abstract A relatively optimal control is a stabilizing controller that, without initialization nor feedforwarding and tracking the optimal trajectory, produces the optimal (constrained) behavior for the nominal initial condition of the plant. In a previous work, a linear dynamic relatively optimal control, for discrete–time linear systems, was presented. Here a static solution is shown, namely a dead–beat piecewise affine state–feedback controller based on a suitable partition of the state space into polyhedral sets. The vertices of the polyhedrons are the states of the optimal trajectory, hence a bound for the complexity of the controller is known in advance. It is also shown how to obtain a controller that is not dead–beat by removing the zero terminal constraint while guaranteeing stability. Finally, the proposed static compensator is compared with the dynamic one. DOI BibTeX
@inproceedings{Blanchini2005,
abstract = "A relatively optimal control is a stabilizing controller that, without initialization nor feedforwarding and tracking the optimal trajectory, produces the optimal (constrained) behavior for the nominal initial condition of the plant. In a previous work, a linear dynamic relatively optimal control, for discrete–time linear systems, was presented. Here a static solution is shown, namely a dead–beat piecewise affine state–feedback controller based on a suitable partition of the state space into polyhedral sets. The vertices of the polyhedrons are the states of the optimal trajectory, hence a bound for the complexity of the controller is known in advance. It is also shown how to obtain a controller that is not dead–beat by removing the zero terminal constraint while guaranteeing stability. Finally, the proposed static compensator is compared with the dynamic one.",
address = "Prague",
author = "Blanchini, Franco and Pellegrino, Felice Andrea",
booktitle = "Proceedings of the 16th IFAC World Congress",
doi = "10.3182/20050703-6-CZ-1902.00513",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini, Pellegrino - 2005 - Relatively Optimal Control the Static Solution(2).pdf:pdf",
keywords = "discrete,invariance,linear systems,optimal control,time systems",
title = "{Relatively Optimal Control: the Static Solution}",
year = 2005
}
Franco Blanchini and Felice Andrea Pellegrino.
Relatively optimal control with characteristic polynomial assignment.
In Proceedings of the 43rd IEEE Conference on Decision and Control 2. 2004, 2171–2176 Vol.2.
Abstract A relatively optimal control is a stabilizing controller such that, if initialized at its zero state, produces the optimal (constrained) behavior for the nominal initial condition of the plant (without feedforwarding and tracking the optimal trajectory). In a previous work we have shown that one of such controllers is linear, dead-beat, and its order is equal to the length of the horizon minus the plant order, thus of complexity which is known a-priori. In this work we remove the assumption of zero terminal state and we show how to assign an arbitrary closed-loop characteristic stable polynomial to the plant (an explicit solution is provided.) We also show how to choose the characteristic polynomial in such a way that the constraints (which are enforced on a finite horizon) can be globally or ultimately satisfied. DOI BibTeX
@inproceedings{Blanchini2004,
abstract = "A relatively optimal control is a stabilizing controller such that, if initialized at its zero state, produces the optimal (constrained) behavior for the nominal initial condition of the plant (without feedforwarding and tracking the optimal trajectory). In a previous work we have shown that one of such controllers is linear, dead-beat, and its order is equal to the length of the horizon minus the plant order, thus of complexity which is known a-priori. In this work we remove the assumption of zero terminal state and we show how to assign an arbitrary closed-loop characteristic stable polynomial to the plant (an explicit solution is provided.) We also show how to choose the characteristic polynomial in such a way that the constraints (which are enforced on a finite horizon) can be globally or ultimately satisfied.",
address = "Atlantis, Paradise Island",
author = "Blanchini, Franco and Pellegrino, Felice Andrea",
booktitle = "Proceedings of the 43rd IEEE Conference on Decision and Control",
doi = "10.1109/CDC.2004.1430370",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini, Pellegrino - 2004 - Relatively optimal control with characteristic polynomial assignment.pdf:pdf",
pages = "2171--2176 Vol.2",
title = "{Relatively optimal control with characteristic polynomial assignment}",
volume = 2,
year = 2004
}
Franco Blanchini, Felice Andrea Pellegrino, Stefano Miani and Bart Arkel.
Enhancing controller performance for robot positioning in a constrained environment.
In Proceedings of the 43rd IEEE Conference on Decision and Control 5. 2004, 5222–5227.
Abstract The paper considers a novel technique for manip- ulator motion in constrained environment due to the presence of obstacles. The basic problem is that of avoiding collisions of the manipulator with the obstacles. The main idea is to cover the free space (i.e. the points of the configurations space in which no collisions are possible) by a connected family of polyhedral sets which are controlled–invariant. Each of these polyhedral regions includes some crossing points to the confining regions. The tracking control is hierarchically struc- tured. A high–level controller establishes a connected chain of regions to be crossed to reach the one in which the reference is included. A low–level control solves the problem of tracking, within a region, the crossing point to the next confining region and, eventually, tracking the reference whenever it is included in the current one. The scheme assures that the reference is asymptotically tracked and that the transient trajectory is completely included in the admissible configuration space. A connection graph associated with the cluster of regions, and the high–level control is achieved by solving a minimum–path problem. As far as the low–level control is concerned, we consider both speed–control and torque–control. We propose two types of controllers. The first type is based on a linear stabilizing feedback which is suitably adapted to achieve a local tracking controller. Such a controller is computed by the plane representation of the sets which is more natural and useful then the vertex representation considered in previous work. The second is a speed–saturated type of controller which considerably improves the performance of linear–based control laws. Both these controllers have a speed–control and torque–control version. Experimental results on a laboratory Cartesian robot are provided. DOI BibTeX
@inproceedings{Blanchini2004b,
abstract = "The paper considers a novel technique for manip- ulator motion in constrained environment due to the presence of obstacles. The basic problem is that of avoiding collisions of the manipulator with the obstacles. The main idea is to cover the free space (i.e. the points of the configurations space in which no collisions are possible) by a connected family of polyhedral sets which are controlled–invariant. Each of these polyhedral regions includes some crossing points to the confining regions. The tracking control is hierarchically struc- tured. A high–level controller establishes a connected chain of regions to be crossed to reach the one in which the reference is included. A low–level control solves the problem of tracking, within a region, the crossing point to the next confining region and, eventually, tracking the reference whenever it is included in the current one. The scheme assures that the reference is asymptotically tracked and that the transient trajectory is completely included in the admissible configuration space. A connection graph associated with the cluster of regions, and the high–level control is achieved by solving a minimum–path problem. As far as the low–level control is concerned, we consider both speed–control and torque–control. We propose two types of controllers. The first type is based on a linear stabilizing feedback which is suitably adapted to achieve a local tracking controller. Such a controller is computed by the plane representation of the sets which is more natural and useful then the vertex representation considered in previous work. The second is a speed–saturated type of controller which considerably improves the performance of linear–based control laws. Both these controllers have a speed–control and torque–control version. Experimental results on a laboratory Cartesian robot are provided.",
address = "Atlantis, Paradise Island",
author = "Blanchini, Franco and Pellegrino, Felice Andrea and Miani, Stefano and van Arkel, Bart",
booktitle = "Proceedings of the 43rd IEEE Conference on Decision and Control",
doi = "10.1109/CDC.2004.1429637",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini et al. - 2004 - Enhancing controller performance for robot positioning in a constrained environment.pdf:pdf",
pages = "5222--5227",
title = "{Enhancing controller performance for robot positioning in a constrained environment}",
volume = 5,
year = 2004
}
Franco Blanchini and Felice Andrea Pellegrino.
Relatively optimal control and its linear implementation.
In Proceedings of the 42nd IEEE Conference on Decision and Control 1(12). 2003, 215–220.
Abstract Motivated by the fact that determining a feedback solution for the optimal control problem under constraints is a hard task we introduce the concept of relative optimality, roughly optimality for a specific (nominal) plant initial condition. We consider a generic discrete-time finite-horizon constrained optimal control problem for linear systems, and we seek for a state feedback (possibly dynamic) controller. As a fundamental requirement, we do not admit preactions or controller-state initialization based on the plant initial state and we assume our controller to be time-invariant. In particular, we do not consider controllers simply achieved by the feedforward and tracking of the optimal trajectory. A relatively optimal control is a stabilizing controller such that, if initialized at its zero state, produces the optimal (constrained) trajectory for the nominal initial condition of the plant. We show that one of such controllers is linear, dead- beat, and its order is equal to the length of the horizon minus the plant order, thus of complexity which is known a-priori. DOI BibTeX
@inproceedings{Blanchini2003c,
abstract = "Motivated by the fact that determining a feedback solution for the optimal control problem under constraints is a hard task we introduce the concept of relative optimality, roughly optimality for a specific (nominal) plant initial condition. We consider a generic discrete-time finite-horizon constrained optimal control problem for linear systems, and we seek for a state feedback (possibly dynamic) controller. As a fundamental requirement, we do not admit preactions or controller-state initialization based on the plant initial state and we assume our controller to be time-invariant. In particular, we do not consider controllers simply achieved by the feedforward and tracking of the optimal trajectory. A relatively optimal control is a stabilizing controller such that, if initialized at its zero state, produces the optimal (constrained) trajectory for the nominal initial condition of the plant. We show that one of such controllers is linear, dead- beat, and its order is equal to the length of the horizon minus the plant order, thus of complexity which is known a-priori.",
address = "Maui, Hawaii",
author = "Blanchini, Franco and Pellegrino, Felice Andrea",
booktitle = "Proceedings of the 42nd IEEE Conference on Decision and Control",
doi = "10.1109/CDC.2003.1272563",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini, Pellegrino - 2003 - Relatively optimal control and its linear implementation.pdf:pdf",
number = 12,
pages = "215--220",
title = "{Relatively optimal control and its linear implementation}",
volume = 1,
year = 2003
}
Felice Andrea Pellegrino, Walter Vanzella and Vincent Torre.
How the spatial filters of area V1 can be used for a nearly ideal edge detection.
In Proceedings of the 2nd International Workshop on Biological Motivated Computer Vision. 2002, 37–49.
Abstract The present manuscript aims to address and possibly solve three classical problems of edge detection: i – the detection of all step edges from a fine to a coarse scale; ii – the detection of thin bars, i.e. of roof edges; iii – the detection of corners and trihedral junctions. The proposed solution of these problems combines an extensive spatial filtering, inspired by the receptive field properties of neurons in the visual area V1, with classical methods of Computer Vision (Morrone & Burr 1988; Lindeberg 1998; Kovesi 1999) and newly developed algorithms. Step edges are computed by extracting local maxima from the energy summed over a large bank of odd filters of different scale and direction. Thin roof edges are computed by considering maxima of the energy summed over narrow odd and even filters along the direction of maximal response. Junctions are precisely detected by an appropriate combination of the output of directional filters. Detected roof edges are cleaned by using a regularization procedure and are combined with step edges and junctions in a Mumford-Shah type functional with self adaptive parameters, providing a nearly ideal edge detection and segmentation. DOI BibTeX
@inproceedings{Pellegrino2002,
abstract = "The present manuscript aims to address and possibly solve three classical problems of edge detection: i – the detection of all step edges from a fine to a coarse scale; ii – the detection of thin bars, i.e. of roof edges; iii – the detection of corners and trihedral junctions. The proposed solution of these problems combines an extensive spatial filtering, inspired by the receptive field properties of neurons in the visual area V1, with classical methods of Computer Vision (Morrone & Burr 1988; Lindeberg 1998; Kovesi 1999) and newly developed algorithms. Step edges are computed by extracting local maxima from the energy summed over a large bank of odd filters of different scale and direction. Thin roof edges are computed by considering maxima of the energy summed over narrow odd and even filters along the direction of maximal response. Junctions are precisely detected by an appropriate combination of the output of directional filters. Detected roof edges are cleaned by using a regularization procedure and are combined with step edges and junctions in a Mumford-Shah type functional with self adaptive parameters, providing a nearly ideal edge detection and segmentation.",
address = {T{\"{u}}bingen},
author = "Pellegrino, Felice Andrea and Vanzella, Walter and Torre, Vincent",
booktitle = "Proceedings of the 2nd International Workshop on Biological Motivated Computer Vision",
doi = "10.1007/3-540-36181-2_4",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Pellegrino, Vanzella, Torre - 2002 - How the spatial filters of area V1 can be used for a nearly ideal edge detection.pdf:pdf",
pages = "37--49",
title = "{How the spatial filters of area V1 can be used for a nearly ideal edge detection}",
year = 2002
}
Franco Blanchini, Stefano Miani and Felice Andrea Pellegrino.
Suboptimal receding horizon control for continuous-time systems.
In Proceedings of the 41st IEEE Conference on Decision and Control. 2002, 1558–1563.
Abstract In this paper, a continuous–time optimal control problem is approached in a sub–optimal way by introducing the concept of suboptimal value function, which is any function satisfying the Hamilton–Jacobi–Bellman inequality. It is shown that as long as the Euler Approximating System (EAS) of a given continuous–time plant admits a positive definite convex suboptimal value function, it is possibile to determine a stabilizing control for the continuous–time system whose cost not only converges to the optimal, but it is also upper bounded by the discrete–time cost no matter how the “discretization time parameter” is chosen. DOI BibTeX
@inproceedings{Blanchini2002,
abstract = "In this paper, a continuous–time optimal control problem is approached in a sub–optimal way by introducing the concept of suboptimal value function, which is any function satisfying the Hamilton–Jacobi–Bellman inequality. It is shown that as long as the Euler Approximating System (EAS) of a given continuous–time plant admits a positive definite convex suboptimal value function, it is possibile to determine a stabilizing control for the continuous–time system whose cost not only converges to the optimal, but it is also upper bounded by the discrete–time cost no matter how the “discretization time parameter” is chosen.",
address = "Las Vegas",
author = "Blanchini, Franco and Miani, Stefano and Pellegrino, Felice Andrea",
booktitle = "Proceedings of the 41st IEEE Conference on Decision and Control",
doi = "10.1109/CDC.2002.1184741",
file = ":Users/felix/OneDrive - Universit{\`{a}} degli Studi di Trieste/Books and papers/Blanchini, Miani, Pellegrino - 2002 - Suboptimal receding horizon control for continuous-time systems.pdf:pdf",
isbn = "0-7803-7516-5",
pages = "1558--1563",
title = "{Suboptimal receding horizon control for continuous-time systems}",
year = 2002
}
