應用基因型案例式推論建置足球賽代理人

Cooperative RoboCup agents using Genetic Case-based Reasoning

林合治(He Zhi Lin)

指導教授 ： 郭忠義

國立臺北科技大學/電資學院/資訊工程系研究所/碩士(2008年)

https://doi.org/10.6841/NTUT.2008.00060

摘要

機器人足球競賽(Robot world cup tournament ,RoboCup)是近年來在國際上發展起來的一種機器人之間的競賽遊戲，許多學術研究也將理論運用在這個有趣的領或上，像是人工智慧、多代理人系統、機器人學等。但在足球機器人的發展上仍有許多的困難必需被克服，像是代理人計劃的產生以及控制機器人時的許多不確定性等，本文將針對足球機器人團隊的計劃學習上提出解決辦法，透過經驗的累積，機器人可運用過去的相似經驗來解決新的問題。好的經驗能提高計劃的成功率，相對的，失敗的經驗能避免機器人犯和過去相同的錯誤。本研究將以此方法運用在樂高機器人上，並記錄機器人執行計劃的成功率來呈現計劃的學習效果。

關鍵字

機器人足球競賽 ； 人工智慧 ； 多代理人系統 ； 機器人學

並列摘要

RoboCup (Robot world cup tournament) soccer game is a competition game. It has already become a popular research domain in recent years. Our research includes complex system behavior of multiple agents. The goal of developing RoboCup is an attempt to promote AI and robotics, and some researchers even wish RoboCup robots can win human soccer players. In this paper, we proposed a hybrid approach to implementing our RoboCup agent. It can provide good strategy for robots planning base on all kinds of conditions and saving experience for future reusage. Robots will grow up by our hybrid approach without prior defining knowledge and complex mathematics basis and can learn by saving experience. The robots not only learn how to score but also learn how to avoid making the same mistakes. And we show the effectiveness of the proposed method by implementing a prototype and by comparing with another learning approach.

並列關鍵字

RoboCup ； hybrid approach

參考文獻

[1] Nguyen Hoang Phuong, Nadipuriun R. Prasad, Dang Huu Hung, Jeffery T. Drake,

“Approach to Combining Case Based Reasoning with Rule Based Reasoning for

[2] Lai Chaoan, “The expert system of product design based on CBR and GA”,

International Conference on Computational Intelligence and Security Workshops,

pp.144-147, 2007.