Informatics Report Series
|
|
|
|
|
|
Title:Behaviour Generation in Humanoids by Learning Potential-based Policies from Constrained Motion |
Authors:
Matthew Howard
; Stefan Klanke
; Michael Gienger
; Christian Goerick
; Sethu Vijayakumar
|
Date:Dec 2008 |
Publication Title:Applied Bionics and Biomechanics |
Publisher:Taylor & Francis |
Publication Type:Journal Article
Publication Status:Pre-print
|
Volume No:5
Page Nos:195-211
|
DOI:10.1080/11762320902789830
|
- Abstract:
-
Movement generation that is consistent with observed or demonstrated behaviour is an efficient way to seed movement planning in complex, high dimensional movement systems like humanoid robots. We present a method for learning potential-based policies from constrained motion data. In contrast to previous approaches to direct policy learning, our method can combine observations from a variety of contexts where different constraints are in force, to learn the underlying unconstrained policy in form of its potential function. This allows us to generalise and predict behaviour where novel constraints apply. We demonstrate our approach on systems of varying complexity, including kinematic data from the ASIMO humanoid robot with 22 degrees of freedom.
- Copyright:
- 2009 by The University of Edinburgh. All Rights Reserved
- Links To Paper
- No links available
- Bibtex format
- @Article{EDI-INF-RR-1322,
- author = {
Matthew Howard
and Stefan Klanke
and Michael Gienger
and Christian Goerick
and Sethu Vijayakumar
},
- title = {Behaviour Generation in Humanoids by Learning Potential-based Policies from Constrained Motion},
- journal = {Applied Bionics and Biomechanics},
- publisher = {Taylor & Francis},
- year = 2008,
- month = {Dec},
- volume = {5},
- pages = {195-211},
- doi = {10.1080/11762320902789830},
- }
|