This talk will address the general topic of cooperative motion planning, navigation, and control of marine vehicles, both from a theoretical and a practical perspective. The presentation builds upon practical developments and experiments. Examples of scientific missions with ASCs and AUVs, acting alone or in cooperation, set the stage for the main contents of the presentation.
Especial emphasis is placed on the problem of operating groups of vehicles for scientific ocean studies, habitat mapping in complex 3D scenarios, geotechnical surveying, and sustained presence at sea in hazardous environments.
From a theoretical standpoint, a number of challenging problems are addressed in the general area of networked systems subjected to stringent communication constraints. Namely, i) Cooperative motion control using event-driven control and communications and ii) range-based multiple target localization and tracking using tools from the areas of optimal motion planning and estimation theory. Some of the the results obtained are illustrated with videos from actual field tests with multiple marine robots exchanging information over acoustic and optical networks.
António Pascoal got his PhD in Control Science from the University of Minnesota, Minneapolis, MN, USA, 1987. He is professor of Control and Robotics at IST, University of Lisbon, Portugal and member of Scientific Council of the Institute for Systems and Robotics (ISR) and founder, Dynamical Systems and Ocean Robotics Lab (DSORLab) of ISR. Coordinates the Thematic Area “Technologies for Ocean Exploration and Exploitation” of the Associate Laboratory of Robotics and Engineering Systems (LARSyS). He is an Adjunct Scientist, National Institute of Oceanography (NIO), Goa India and a visiting Faculty, Department of Ocean Engineering, IIT Madras, under the Indian Sparc Programme. Expertise in Dynamical Systems Theory, Marine Robotics, Navigation, Guidance, and Control of Autonomous Vehicles, and Networked Control and Estimation with applications to air and underwater robots, is long-term goal is to contribute to the development of advanced robotic systems for ocean resources exploration and exploitation.
In this talk, we investigate a general framework suitable for learning motor skills in robotics which is based on the principles behind many analytical robotics approaches. It involves generating a representation of motor skills by parameterized motor primitive policies acting as building blocks of movement generation, and a learned task execution module that transforms these movements into motor commands.
We discuss learning on three different levels of abstraction, i.e., learning for accurate control is needed to execute, learning of motor primitives is needed to acquire simple movements, and learning of the task-dependent “hyperparameters“ of these motor primitives allows learning complex tasks. We discuss task-appropriate learning approaches for imitation learning, model learning and reinforcement learning for robots with many degrees of freedom.
Empirical evaluations on a several robot systems illustrate the effectiveness and applicability to learning control on an anthropomorphic robot arm. These robot motor skills range from toy examples (e.g., paddling a ball, ball-in-a-cup) to playing robot table tennis against a human being and manipulation of various objects.
Jan Peters is a full professor (W3) for Intelligent Autonomous Systems at the Computer Science Department of the Technische Universitaet Darmstadt and at the same time a senior research scientist and group leader at the Max-Planck Institute for Intelligent Systems, where he heads the interdepartmental Robot Learning Group. Jan Peters has received the Dick Volz Best 2007 US PhD Thesis Runner-Up Award, the Robotics: Science & Systems – Early Career Spotlight, the INNS Young Investigator Award, and the IEEE Robotics & Automation Society’s Early Career Award as well as numerous best paper awards. In 2015, he received an ERC Starting Grant and in 2019, he was appointed as an IEEE Fellow. Despite being a faculty member at TU Darmstadt only since 2011, Jan Peters has already nurtured a series of outstanding young researchers into successful careers. These include new faculty members at leading universities in the USA, Japan, Germany and Holland, postdoctoral scholars at top computer science departments (including MIT, CMU, and Berkeley) and young leaders at top AI companies (including Amazon, Google and Facebook).