Robot Control, Learning and Teleoperation

15^th March 2024, 13:00 ELEC 202
Chenguang (Charlie) Yang

Abstract

Nowadays robots are expected to be of increasing intelligence to deal with a large range of tasks. Especially, robots are supposed to be able to learn skills from our humans and perform dexterous manipulation in a human-like manner. A number of learning algorithms and techniques have been developed and successfully implemented for various robotic tasks. Among these methods, learning from demonstrations (LfD) enables robots to effectively and efficiently acquire skills by learning from human demonstrators, such that a robot can be quickly programmed to perform new tasks. This talk will present my recent research progress on human-in-the-loop learning for robots to acquire and generalize manipulation skills. It will also introduce my studies on human-like control design inspired by human motor behaviors from more than a decade ago. The control and learning technologies I developed have been particularly applied to robot teleoperation, for which I have also extensively investigated human robot interaction interface.