Reinforcement Learning Based Track Solving Control on a Humanoid Robot
Deng, Dechen
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/54547
Description
Title
Reinforcement Learning Based Track Solving Control on a Humanoid Robot
Author(s)
Deng, Dechen
Contributor(s)
Levinson, Stephen
Issue Date
2014-05
Keyword(s)
Reinforced learning
Humanoid robot
Abstract
For a long time people have debated about whether an artificial intelligence can
learn like human beings. Whether it is possible for them to learn a skill or an ability through human or environmental
interaction continues to raise discussions. Thus, in a small part of this discussion, I
implemented a reinforcement learning based control of a ball
on a track using a humanoid robot called iCub. The robot uses a camera as an eyeball to see the
world and uses sensory-motor feedback to control the ball based on the policy learned from the feedback of
the environment. In the process, I used Q-learning, a reinforcement learning algorithm for the
policy learning and I also implemented a simple computer vision method to track the ball. This
experiment reveals that a robot has the ability to interact with the environment and even with
people.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
