Seminar “A Synergetic Approach to Increase Mobility Awareness in Legged Robots”

2022-06-29

Don´t miss the seminar on the 1st of July, by Prof. Dr. Michele Focchi from Università di Trento. The seminar is open to all FEUP community and will be taking place in room i205, at 10:30.

ABSTRACT

Legged robots are mainly designed to traverse unstructured environments where wheeled robots have limited mobility. Their applications range from nuclear decommissioning to mining, search and rescue, inspection and surveillance. In addition, they can be applied to flank human workers (or collaborate with them) in order to reduce labor accidents. The next generation of legged robots are envisioned to operate either autonomously or semi-autonomously (through tele-operation) over uneven terrains.

This requires the capability to comply with disturbances, to wisely exploit information from the visual feedback, and the ability to manipulate objects or interact with the environment. Therefore, the main ingredients for legged locomotion are planning, control, perception and state estimation. In this talk I will present research results in these fields obtained in more than ten years of experience in legged locomotion. Moreover, I will illustrate my future research vision, that encompasses two research axes: 1) explore novel applications for legged robots. 2) enhance the motion capability of legged robots through the use of numerical optimization in planning trajectories.

Indeed, optimization-based planning strategies enable to generalize motions to address different terrains and complex motions. With respect to more myopic heuristic approaches (that lack awareness of the future) they give the possibility to reach the robot performance limits and to guarantee physical feasibility of the planned trajectories, because they take into account the hardware constraints that are typical of legged robots (kinematic and actuation limits) and the interaction with the environment.

BIO

Michele Focchi is currently a Researcher at Università di Trento and a visiting scientist at Istituto Italiano di Tecnologia. He received both the Bsc. and the Msc. in Control System Engineering from Politecnico di Milano. In 2009 he joined IIT where he developed a micro-turbine for which he obtained an international patent. In 2013, he got a PhD in robotics, getting involved in the Hydraulically Actuated Quadruped Robot project.

He was developing torque controllers for locomotion purposes, subsequently he moved to higher level (whole-body) controllers. He was also investigating locomotion strategies that are robust to uncertainties and work reliably on real platforms. Currently his research interests are focused on pushing the performances of legged robots in traversing unstructured environments, by using optimization-based planning strategies to perform dynamic motion planning.  He is also envisioning novel designs of rope-aided robot for exploration purposes.

He was a leader of the ANT project with the European Space Agency with the aim to develop navigation system for space exploration. On 2022 he joined University of Trento where he started to teach courseson Robotics. He published more than 42 papers in international journals an conferences and supervised several master and PhD thesis.

Tags