Skip to main navigation Skip to search Skip to main content

Research of reinforcement learning based share control of walking-aid robot

  • Wenxia Xu
  • , Jian Huang
  • , Yongji Wang
  • , Chunjing Tao
  • , Xueshan Gao
  • Huazhong University of Science and Technology
  • National Research Center for Rehabilitation Technical Aids
  • Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper we developed a new reinforcement learning based share control algorithm for walking-aid robot. We use a group of one-dimensional push-pull force sensors to estimate human walking intention, from which the user's desired moving velocity of robot is obtained. At the same time, the robot itself also plans a desired moving velocity. A weighted sum of the two desired velocities is taken as the real reference velocity and fed into the motion controller. The Sarsa-learning algorithm dynamically adapts the weights of user's control according to the control efficiency, the robot state and the environment. As a result, an optimal share control for walking-aid robot is realized in a certain environment. Finally experiments are performed to verify the effectiveness of algorithm.

Original languageEnglish
Title of host publicationProceedings of the 32nd Chinese Control Conference, CCC 2013
PublisherIEEE Computer Society
Pages5883-5888
Number of pages6
ISBN (Print)9789881563835
StatePublished - 18 Oct 2013
Externally publishedYes
Event32nd Chinese Control Conference, CCC 2013 - Xi'an, China
Duration: 26 Jul 201328 Jul 2013

Publication series

NameChinese Control Conference, CCC
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

Conference32nd Chinese Control Conference, CCC 2013
Country/TerritoryChina
CityXi'an
Period26/07/1328/07/13

Keywords

  • Reinforcement Learning
  • Share Control
  • Walking-aid Robot

Fingerprint

Dive into the research topics of 'Research of reinforcement learning based share control of walking-aid robot'. Together they form a unique fingerprint.

Cite this