Avviso di Sminario "Aerial motions for legged robots"
Abstract:
In this talk, I will present my research on enhancing robotic motion and control across diverse and challenging scenarios.
First, I will explore the generation of optimal jumping motions using Reinforcement Learning (RL), integrating physical insights to guide the learning process.
This significantly reduces the training time compared to standard end-to-end approaches.
Second, I will illustrate the development of novel robotic platforms that combine ropes and legged systems to address the challenges of maintenance in remote, hazardous environments. By leveraging optimal control techniques, I designed a computationally efficient planning algorithm for precise and adaptive jumping motions.
Bio sketch:
Michele Focchi is a world-recognized expert in motion planning and control of quadruped robots, with over 16 years of experience in robotics research. He is currently a Professor at the University of Trento in the Department of Information Engineering and Computer Science (DISI), where he teaches robotics courses at the bachelor, master, and PhD levels. He is also a Scientific Advisor for industrial partners like All3 Robotics.
Prof. Focchi earned both his B.Sc. and M.Sc. degrees in Control Systems Engineering from Politecnico di Milano and completed his Ph.D. in Robotics at Italian Institute of Technology in 2013, contributing to the development of the first Italian quadruped robot (HyQ). During his time at IIT, he co-founded the Dynamic Legged Systems Lab, an internationally recognized research team focused on the development of quadruped robots and advanced locomotion strategies. His research lies at the intersection of control, optimization, and machine learning, with a strong focus on optimization-based and Model Predictive Control techniques for robust locomotion in unstructured and challenging environments. His work has evolved from low-level locomotion controllers to whole-body control, model identification, and uncertainty-aware motion planning for real-world applicatoms. He is particularly known for his pioneering contributions to heuristic locomotion strategies for quadruped robots operating in rough terrain. Beyond quadruped locomotion, Prof. Focchi has developed and studied innovative robotic platforms, including rappelling robots for hydro-geological risk reduction and inspection in oil & gas scenarios, as well as control and navigation strategies for tracked robots in agricultural applications. He has played leading roles in several high-profile academic and industrial projects, including ECHORD++, INAIL, and ANT with the European Space Agency (ESA) and, more recently, EUREGIO and VRT.
In 2015, he co-founded the MOOG–IIT Joint Lab, focused on the development of next-generation software and control technologies for autonomous robots. He is the inventor and co-inventor of several patents; notably, in 2009 he contributed to a patented micro-turbine technology that led to the creation of the Advanced Microturbines spin-off company. He has organized several scientific workshops, including a workshop on numerical optimization at Robotics: Science and Systems (RSS), and has delivered more than 25 invited talks at international conferences and workshops.
He is the organizer of the first PhD summer school on Quadruped Robots and Dog Challenges in Italy. He has authored or co-authored 50+ scientific publications in top international journals and conferences and has supervised numerous master’s and Ph.D. theses. He currently serves as an Associate Editor for IEEE Robotics and Automation Letters (RA-L) and for the IEEE International Conference on Robotics and Automation (ICRA).