Nicola Lissandrini; Giulia Michieletto; Riccardo Antonello; Marta Galvan; Alberto Franco; Angelo Cenedese Cooperative Optimization of UAVs Formation Visual Tracking (Journal Article) Robotics, 8 (3), pp. 1–22, 2019. (Abstract | Links | BibTeX | Tags: coverage, multi-agent, optimization, UAVs, visual tracking) @article{Lissandrini2019, title = {Cooperative Optimization of UAVs Formation Visual Tracking}, author = {Nicola Lissandrini and Giulia Michieletto and Riccardo Antonello and Marta Galvan and Alberto Franco and Angelo Cenedese }, url = {https://www.mdpi.com/2218-6581/8/3/52}, doi = {https://doi.org/10.3390/robotics8030052}, year = {2019}, date = {2019-07-07}, journal = { Robotics}, volume = {8}, number = {3}, pages = {1--22}, abstract = {The use of unmanned vehicles to perform tiring, hazardous, repetitive tasks, is becoming a reality out of the academy laboratories, getting more and more interest for several application fields from the industrial, to the civil, to the military contexts. In particular, these technologies appear quite promising when they employ several low-cost resource-constrained vehicles leveraging their coordination to perform complex tasks with efficiency, flexibility, and adaptation that are superior to those of a single agent (even if more instrumented). In this work, we study one of said applications, namely the visual tracking of an evader (target) by means of a fleet of autonomous aerial vehicles, with the specific aim of focusing on the target so as to perform an accurate position estimation while concurrently allowing a wide coverage over the monitored area so as to limit the probability of losing the target itself. These clearly conflicting objectives call for an optimization approach that is here developed: by considering both aforementioned aspects and the cooperative capabilities of the fleet, the designed algorithm allows controling in real time the single fields of view so as to counteract evasion maneuvers and maximize an overall performance index. The proposed strategy is discussed and finally assessed through the realistic Gazebo-ROS simulation framework.}, keywords = {coverage, multi-agent, optimization, UAVs, visual tracking}, pubstate = {published}, tppubtype = {article} } The use of unmanned vehicles to perform tiring, hazardous, repetitive tasks, is becoming a reality out of the academy laboratories, getting more and more interest for several application fields from the industrial, to the civil, to the military contexts. In particular, these technologies appear quite promising when they employ several low-cost resource-constrained vehicles leveraging their coordination to perform complex tasks with efficiency, flexibility, and adaptation that are superior to those of a single agent (even if more instrumented). In this work, we study one of said applications, namely the visual tracking of an evader (target) by means of a fleet of autonomous aerial vehicles, with the specific aim of focusing on the target so as to perform an accurate position estimation while concurrently allowing a wide coverage over the monitored area so as to limit the probability of losing the target itself. These clearly conflicting objectives call for an optimization approach that is here developed: by considering both aforementioned aspects and the cooperative capabilities of the fleet, the designed algorithm allows controling in real time the single fields of view so as to counteract evasion maneuvers and maximize an overall performance index. The proposed strategy is discussed and finally assessed through the realistic Gazebo-ROS simulation framework. |
Luca Varotto; Alessandra Zampieri; Angelo Cenedese Street Sensor Set Selection through Map Segmentation and Observability Measures (Inproceedings) 2019. (Abstract | BibTeX | Tags: optimization, sensor networks, sensor selection) @inproceedings{Varotto2019street, title = {Street Sensor Set Selection through Map Segmentation and Observability Measures}, author = {Luca Varotto and Alessandra Zampieri and Angelo Cenedese }, year = {2019}, date = {2019-07-03}, journal = {Mediterranean Conference on Control and Automation 2019}, abstract = {Nowadays, vehicle flow monitoring, model-based traffic management, and congestion prediction are becoming fundamental elements for the realization of the Smart City paradigm. These tasks usually require wide sensor deployments, but, due to economical, practical, and environmental constraints, they must be accomplished with a limited number of sensors. Thus motivated, this work addresses the sensors selection problem for urban street monitoring, by employing a road map image as the basic information and considering the placement of at most one sensor along each road with a chosen number of available devices. To solve the problem, the concept of system observability is exploited as the criterium for optimal sensor placement, specifically related to the capability of estimating the traffic flow in each road using the available output measurements. In this framework, different integer non- linear programming problems are proposed, whose solutions are studied and analyzed by means of numerical simulations on a real case scenario.}, keywords = {optimization, sensor networks, sensor selection}, pubstate = {published}, tppubtype = {inproceedings} } Nowadays, vehicle flow monitoring, model-based traffic management, and congestion prediction are becoming fundamental elements for the realization of the Smart City paradigm. These tasks usually require wide sensor deployments, but, due to economical, practical, and environmental constraints, they must be accomplished with a limited number of sensors. Thus motivated, this work addresses the sensors selection problem for urban street monitoring, by employing a road map image as the basic information and considering the placement of at most one sensor along each road with a chosen number of available devices. To solve the problem, the concept of system observability is exploited as the criterium for optimal sensor placement, specifically related to the capability of estimating the traffic flow in each road using the available output measurements. In this framework, different integer non- linear programming problems are proposed, whose solutions are studied and analyzed by means of numerical simulations on a real case scenario. |
List of Publications
Cooperative Optimization of UAVs Formation Visual Tracking (Journal Article) Robotics, 8 (3), pp. 1–22, 2019. |
Street Sensor Set Selection through Map Segmentation and Observability Measures (Inproceedings) 2019. |