Learning for Control from Multiple Demonstrations
published: Aug. 12, 2008, recorded: July 2008, views: 10455
Download slides: icml08_coates_lcmd_01.pdf (429.2 KB)
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
We consider the problem of learning to follow a desired trajectory when given a small number of demonstrations from a sub-optimal expert. We present an algorithm that (i) extracts the---initially unknown---desired trajectory from the sub-optimal expert's demonstrations and (ii) learns a local model suitable for control along the learned trajectory. We apply our algorithm to the problem of autonomous helicopter flight. In all cases, the autonomous helicopter's performance exceeds that of our expert helicopter pilot's demonstrations. Even stronger, our results significantly extend the state-of-the-art in autonomous helicopter aerobatics. In particular, our results include the first autonomous tic-tocs, loops and hurricane, vastly superior performance on previously performed aerobatic maneuvers (such as in-place flips and rolls), and a complete airshow, which requires autonomous transitions between these and various other maneuvers.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !
Reviews and comments:
Can you please shoot the cameraman. As a keen flyer myself I was interested in how they managed to teach the computer to fly a helicopter. Yet the cameraman was more interested in the looking at the speaker. WHY? I can hear what he is saying without having to look at him. So when he spoke about a point on a slide I could not see it since the camera was looking at the him.
How many of us watch the commentator of a sports event, rather than the event itself?
Write your own review or comment: