• DocumentCode
    411595
  • Title

    A reinforcement-learning approach to robot navigation

  • Author

    Su, Mu-Chun ; Huang, De-Yuan ; Chou, Chien-Hsing ; Hsieh, Chen-Chiung

  • Author_Institution
    Dept. of Comput. Sci & Inf. Eng., Nat. Central Univ., Chung-li, Taiwan
  • Volume
    1
  • fYear
    2004
  • fDate
    21-23 March 2004
  • Firstpage
    665
  • Abstract
    This paper presents a reinforcement-learning approach to a navigation system which allows a goal-directed mobile robot to incrementally adapt to an unknown environment. Fuzzy rules which map current sensory inputs to appropriate actions are built through the reinforcement learning. Simulation results illustrate the performance of the proposed navigation system. In this paper, ACSNFIS is used as the main network architecture to implement the reinforcement-learning based navigation system.
  • Keywords
    fuzzy neural nets; fuzzy set theory; learning (artificial intelligence); mobile robots; navigation; classifier system based neurofuzzy inference system; fuzzy rules; goal directed mobile robot; navigation system; reinforcement learning; robot navigation; Computer architecture; Computer science; Fuzzy neural networks; Fuzzy systems; Inference algorithms; Machine learning algorithms; Mobile robots; Navigation; Path planning; Service robots;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Networking, Sensing and Control, 2004 IEEE International Conference on
  • ISSN
    1810-7869
  • Print_ISBN
    0-7803-8193-9
  • Type

    conf

  • DOI
    10.1109/ICNSC.2004.1297519
  • Filename
    1297519