Title: “Planning and Perception on HyQ: Real-Time and On-Board”
Quadrupedal animals move with skill, grace and agility. Quadrupedal robots have made tremendous progress in the last few years. One of the key challenges for successful deployment has been to seamlessly combine planning, perception and control -processes that by definition operate in radically different time-scales in a framework that can operate in real-time and on-borad, on commodity hardware. In this talk I will give an overview of our work with the Hydraulic Quadruped -HyQ- and present our latest framework for perception, planning and control of quadrupedal locomotion in challenging environments.
Ioannis is a post-doctoral researcher at the IDIAP Research Institute in Switzerland. He used to be a post-doctoral researcher at the Dynamic Legged Systems Lab of the Advanced Robotics Department in the Italian Institute of Technology. His research combines motion planning and control with machine learning, focusing on legged robots. His interests include legged locomotion, motion planning, machine learning, and dynamic whole-body motion generation. Previously he worked on machine learning for robot skills at the School of Informatics of the University of Edinburgh, where he received his MSc in Artificial Intelligence and PhD in Informatics.