How to Train Your Robot? A talk by Dr Petar Kormushev

Dr Petar Kormushev with Robot DE NIRO

Dr Petar Kormushev gave a talk to ICRS members about robotics and machine learning on 16th November, 2016. There were also live demos with Robot DE NIRO.

Dr Kormushev is Director of the Robot Intelligence Lab.

A video recording of the talk can be found here:
//www.imperial.ac.uk/robot-intelligence/videos/talks/

Abstract of the talk
In the near future, most households will likely have a domestic robot. But how would you teach your robot new tasks? Endowing robots with human-like abilities to perform physical tasks in a smooth and natural way has been a dream of many researchers. Ideally, robots should be able to acquire new skills through natural interaction with humans. However, acquiring new motor skills is not simple and involves various forms of learning. Some tasks can be successfully transferred to a robot using only imitation strategies. Other tasks can be learned better by the robot alone using reinforcement learning. The key to an efficient learning process lies in the interaction between imitation and self-improvement strategies. The talk will summarize the existing methods for robot learning of new motor skills. A variety of example tasks will be presented, such as learning to manipulate objects, learning efficient bipedal locomotion, whole-body motor skill learning, learning to recover from failures, etc. Throughout these examples, the important role of the learning algorithms will be highlighted, and their limitations revealed. The talk will finish with a glimpse of the cutting-edge research on deep reinforcement learning for robotics.