Proceedings of the KIEE Conference (대한전기학회:학술대회논문집)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

Action Selection by Voting with Loaming Capability for a Behavior-based Control Approach

행동기반 제어방식을 위한 득점과 학습을 통한 행동선택기법

  • Jeong, S.M. (Intelligent System Control Research Center, KIST) ;
  • Oh, S.R. (Intelligent System Control Research Center, KIST) ;
  • Yoon, D.Y. (Intelligent System Control Research Center, KIST) ;
  • You, B.J. (Intelligent System Control Research Center, KIST) ;
  • Chung, C.C. (Division of Electrical and Computer Engineering, Hanyang University)
  • 정석민 (한국과학기술연구원 지능제어센터) ;
  • 오상록 (한국과학기술연구원 지능제어센터) ;
  • 윤도영 (한국과학기술연구원 지능제어센터) ;
  • 유범재 (한국과학기술연구원 지능제어센터) ;
  • 정정주 (한양대학교 공과대학 전자전기컴퓨터 공학부)
  • Published : 2002.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

The voting algorithm for action selection performs self-improvement by Reinforcement learning algorithm in the dynamic environment. The proposed voting algorithm improves the navigation of the robot by adapting the eligibility of the behaviors and determining the Command Set Generator (CGS). The Navigator that using a proposed voting algorithm corresponds to the CGS for giving the weight values and taking the reward values. It is necessary to decide which Command Set control the mobile robot at given time and to select among the candidate actions. The Command Set was learnt online by means as Q-learning. Action Selector compares Q-values of Navigator with Heterogeneous behaviors. Finally, real-world experimentation was carried out. Results show the good performance for the selection on command set as well as the convergence of Q-value.

Keywords