Please use this identifier to cite or link to this item: https://doi.org/10.1017/S0263574702004290
Title: Dynamic bipedal walking assisted by learning
Authors: Chew, C.-M. 
Pratt, G.A.
Keywords: Bipedal walking
CMAC
Q-learning
Reinforcement learning
Virtual model control
Issue Date: Sep-2002
Citation: Chew, C.-M., Pratt, G.A. (2002-09). Dynamic bipedal walking assisted by learning. Robotica 20 (5) : 477-491. ScholarBank@NUS Repository. https://doi.org/10.1017/S0263574702004290
Abstract: This paper presents a general control architecture for bipedal walking which is based on a divide-and-conquer approach. Based on the architecture, the sagittal-plane motion-control algorithm is formulated using a control approach known as Virtual Model Control. A reinforcment learning algorithm is used to learn the key parameter of the swing leg control task so that speed control can be achieved. The control algorithm is applied to two simulated bipedal robots. The simulation analyses demonstrate that the local speed control mechanism based on the stance ankle is effective in reducing the learning time. The algorithm is also demonstrated to be general in that it is applicable across bipedal robots that have different length and mass parameters.
Source Title: Robotica
URI: http://scholarbank.nus.edu.sg/handle/10635/60003
ISSN: 02635747
DOI: 10.1017/S0263574702004290
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

42
checked on Jul 17, 2018

WEB OF SCIENCETM
Citations

42
checked on Jun 27, 2018

Page view(s)

42
checked on Jul 6, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.