Self-Partitioning State Space for Behavior Acquisition of Vision-Based Mobile Robots

Takayuki Nakamura and Tsukasa Ogasawara

Nara Institute of Science and Technology, Graduate School of Information Sciences, Takayama-cho 8916-5, Ikoma, Nara 630-0101, Japan

Received:

October 10, 2000

Accepted:

December 7, 2001

Published:

December 20, 2001

Keywords:

self-partitioning algorithm, reinforcement learning, vision-based mobile robots, soccer robots

Abstract

An input generalization problem is one of the most important in applying reinforcement learning to real robot tasks. To cope with this problem, we propose a self-partitioning state space algorithm, which can make nonuniform quantization of state space. To show that our algorithm has generalization capability, we apply our method to two tasks in which a soccer robot shoots a ball into a goal and prevent a ball from entering a goal. To show the validity of this method, the experimental results for computer simulation and a real robot are shown.

Cite this article as:

T. Nakamura and T. Ogasawara, “Self-Partitioning State Space for Behavior Acquisition of Vision-Based Mobile Robots,” J. Robot. Mechatron., Vol.13 No.6, pp. 625-636, 2001.

Data files:

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.