人間オペレータの技量のカオス・エントロピ解析とファジィ制御による獲得 : 倒立振子の安定化制御における時系列データからの個人差の同定(D&D 2008)

元データ 2009-05-25

概要

In order to stabilize the inherent unstable system like the inverted pendulum on a cart, severe judgment of situation is required. Accordingly, it can be expected that the human operators exhibit a complex behavior occasionally. This paper tries to identify the individual difference of human operator's behavior from time series data by using fuzzy inference and acquire individual skill of human operator. It also investigated the chaotic behavior of human operator and the possibility of the formation of complex system in the learning process of the human operator with difficult control objects. The operators in the experiment are skilled to some extent in stabilizing the inverted pendulum by training, and the data of ten trials per person were successively taken for an analysis, where the waveforms of pendulum angle and cart displacement were recorded. The maximum Lyapunov exponents were estimated from experimental time series data against embedding dimensions. It was found that the rules identified for a fuzzy controller from time series data of each operator showed well the human-generated decision-making characteristics with the chaos and the large amount of disorder. And the individual difference of chaotic and complex human operation can be identified with fuzzy inference.

著者

貝瀬 徹 兵庫県立大学
川副 嘉彦 埼玉工業大学工学部
伊倉 良明 埼玉工業大学大学院工学研究科
松本 仁 (株)東和コンピュータマネジメント
川副 嘉彦 埼玉工業大学 工学部ヒューマン・ロボット学科
貝瀬 徹 兵庫県立大学経営学部
川副 嘉彦 埼玉工業大学 大学院工学系研究科 システム工学専攻
川副 嘉彦 埼玉工業大学

関連論文

▼もっと見る