以演化模糊系統建置足球代理人

An Evolutionary Fuzzy Logic System in RoboCup Soccer Game

歐元正(Yuan-Cheng Ou)

指導教授 ： 郭忠義

國立臺北科技大學/電資學院/電資碩士班/碩士(2009年)

https://doi.org/10.6841/NTUT.2009.00087

摘要

RoboCup(原名Robot World Cup Initiative)是一個國際性的教育研究組織，旨在透過一個標準的問題－機器人世界盃足球賽(RoboCup World Championship and Conference，簡稱RoboCup)來促進人工智慧與機器人科學領域的發展。在機器人科學－機器學習的議題中，有效率的行為學習方法是重要的研究課題。對於智慧型系統的設計而言，讓機器人在面對動態的環境中，能夠經過學習的過程而做出最佳的回應動作，將是極具挑戰性的問題。本文以一種混合式的技術架構，以規則庫的方式來呈現機器人的知識背景，利用模糊推論的方式來控制機器人高階的行為動作，並結合基因演算法將模糊規則逐步最佳化以適應動態的環境，達成機器人行為演化的目的。最後於RoboCup模擬平台上(RoboCup Soccer Simulator)實作驗證，使足球機器人針對高階的行為動作具備學習演進的能力，並在系統的執行速度與機器學習的效率上做分析與探討。

關鍵字

模糊邏輯 ； 基因演算法 ； Hybrid intelligent system ； RoboCup

並列摘要

RoboCup is an international joint project to promote AI, robotics, and related fields. It is an attempt to foster artificial intelligence and robotics research by providing a standard problem where a wide range of technologies can be integrated and examined. The problem of an effective behavior learning of autonomous robots is one of the most important tasks of the modern robotics. In fact, it is well known that the learning to optimize actions of autonomous agents in a dynamic environment is one of the most complex challenges of the intelligent system design. In this paper, we propose a hybrid approach integrating fuzzy logic system with genetic algorithm for high-level skills learning of robots within the RoboCup simulation soccer domain. Through the experiments, we found that the proposed method has good property of computation efficiency and also has a good advantage applied to the environment of RoboCup.

並列關鍵字

Fuzzy logic control ； Genetic algorithm ； Hybrid intelligent system ； RoboCup

參考文獻

[47] H. Z. Lin. Cooperative RoboCup agents using Genetic Case-based Reasoning. Master thesis, National Taipei University of Technology, Taipei, Taiwan, 2008.

[48] F. Y. Hsieh. Adaptive and Cooperative Learning for RoboCup agents. Master thesis, National Taipei University of Technology, Taiwan, 2008.

[4] A. Rao, and M. Georgeff, “BDI Agents: From Theory to Practice”, International Conference on Multi-Agent Systems, 1995.

[5] L. Vig, J. A. Adams, “Multi-robot coalition formation”, IEEE Transactions on Robotics, Vol. 22, Issue 4, pp. 637-649, 2006.

[6] L. A. Zadeh, “Outline of a new approach to the analysis of complex system and decision processed”, IEEE Transactions on Systems, Man and Cybernetics, vol. 3, no. 1, pp. 28-44, 1973.