9 October 1998 Decentralized reinforcement-learning control and emergence of motion patterns
Author Affiliations +
Proceedings Volume 3523, Sensor Fusion and Decentralized Control in Robotic Systems; (1998) https://doi.org/10.1117/12.327004
Event: Photonics East (ISAM, VVDC, IEMB), 1998, Boston, MA, United States
Abstract
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 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.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mikhail Svinin, Kazuyaki Yamada, Kazuhiro Okhura, Kanji Ueda, "Decentralized reinforcement-learning control and emergence of motion patterns", Proc. SPIE 3523, Sensor Fusion and Decentralized Control in Robotic Systems, (9 October 1998); doi: 10.1117/12.327004; https://doi.org/10.1117/12.327004
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Multiagent robotic systems' ambient light sensor
Proceedings of SPIE (May 16 2017)
Peer to peer model for the area coverage and cooperative...
Proceedings of SPIE (September 15 2004)
Sensor-guided parking system for a carlike robot
Proceedings of SPIE (July 30 1998)
Behavior-based cognitive control for mobile robots
Proceedings of SPIE (January 25 1998)
Mobile robot system for the handicapped
Proceedings of SPIE (March 01 1991)

Back to Top