Learning Classifier System on a humanoid NAO robot in dynamic environments

Chang Wang*, Pascal Wiggers, Koen Hindriks, Catholijn M. Jonker

*Corresponding author for this work

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

Abstract

We present a modified version of Extended Classifier System (XCS) on a humanoid NAO robot. The robot is capable of learning a complete, accurate, and maximally general map of an environment through evolutionary search and reinforcement learning. The standard alternation between explore and exploit trials is revised so that the robot relearns only when necessary. This modification makes the learning more effective and provides the XCS with external memory to evaluate the environmental change. Furthermore, it overcomes the drawbacks of learning rate settings in traditional XCS. A simple object seeking task is presented which demonstrates the desirable adaptivity of LCS for a sequential task on a real robot in dynamic environments.

Original languageEnglish
Title of host publication2012 12th International Conference on Control, Automation, Robotics and Vision, ICARCV 2012
Pages94-99
Number of pages6
DOIs
Publication statusPublished - 1 Dec 2012
Externally publishedYes
Event2012 12th International Conference on Control, Automation, Robotics and Vision, ICARCV 2012 - Guangzhou, China
Duration: 5 Dec 20127 Dec 2012

Conference

Conference2012 12th International Conference on Control, Automation, Robotics and Vision, ICARCV 2012
CountryChina
CityGuangzhou
Period5/12/127/12/12

    Fingerprint

Cite this

Wang, C., Wiggers, P., Hindriks, K., & Jonker, C. M. (2012). Learning Classifier System on a humanoid NAO robot in dynamic environments. In 2012 12th International Conference on Control, Automation, Robotics and Vision, ICARCV 2012 (pp. 94-99). [6485140] https://doi.org/10.1109/ICARCV.2012.6485140