Decentralized reinforcement learning control and emergence of motion patterns

M. Svinin, K. Yamada, K. Okhura, K. Ueda

研究成果: Contribution to journalConference article査読

1 被引用数 (Scopus)

抄録

In this paper we propose a system for studying emergence of motion patterns in autonomous mobile robotic systems. The system implements an instance-based reinforcement learning control. Three spaces are of importance in formulation of the control scheme. They are the work space, the sensor space, and the action space. Important feature of our system is that all these spaces are assumed to be continuous. The core part of the system is a classifier system. Based on the sensory state space analysis. The control is decentralized and is specified and is specified at the lowest level of the control system. However, the local controllers are implicitly connected through the perceived environment information. Therefore, they constitute a dynamic environment with respect to each other. The proposed control scheme is tested under simulation for a mobile robot in a navigation task. It is shown that some patterns of global behavior - such as collision avoidance, wall-following, light-seeking - can emerge from the local controllers.

本文言語英語
ページ(範囲)223-234
ページ数12
ジャーナルProceedings of SPIE - The International Society for Optical Engineering
3523
DOI
出版ステータス出版済み - 12 1 1998
イベントSensor Fusion and Decentralized Control in Robotic Systems IV - Boston, MA, 米国
継続期間: 11 2 199811 3 1998

All Science Journal Classification (ASJC) codes

  • 電子材料、光学材料、および磁性材料
  • 凝縮系物理学
  • コンピュータ サイエンスの応用
  • 応用数学
  • 電子工学および電気工学

フィンガープリント

「Decentralized reinforcement learning control and emergence of motion patterns」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル