動的再構成可能ロボットシステムに関する研究 : 第18報,自律分散システムの最適形態を実現する進化的計画法

概要

論文の詳細を見る
This paper discusses an optimization method of multi-agent system. A method for optimization called "evolutional programming" based on genetic algorithms is proposed and addressed. Evolutional programming can be applied to optimization of ill-structured systems such as multi-agent systems. As an example of multi-agent systems, the intelligence system of cellular robotic systems called CEBOT which has been previously studied by us is discussed. The intelligence system of CEBOT consists of many kinds of knowledge sources, which have simple levels of data and intelligence, together with some blackboards, which dynamically organize a hierarchical structure in order to optimize its own performance index. To realize optimal self-organization and self-evolution, evolutional programming is applied. The efficiency of the algorithm is shown by some simulations of self-organization and self-evolution of the intelligence system.
1994-12-25