2005 | OriginalPaper | Buchkapitel
Generating Smart Robot Controllers Through Co-evolution
verfasst von : Kouichi Sakamoto, Qiangfu Zhao
Erschienen in: Embedded and Ubiquitous Computing – EUC 2005 Workshops
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
To evolve robot controllers that generalize well, we should evaluate the controllers using as many environment patterns (evaluation patterns) as possible. However, to evolve the controllers faster, we should use as few evaluation patterns as possible in evaluation. It is difficult to know in advance what patterns can produce good controllers. To solve this problem, this paper studies co-evolution of the robot controllers and the evaluation patterns. To improve the effectiveness of co-evolution, we introduce fitness sharing in the population of evaluation patterns, and the inter-generation fitness in selecting good controllers. Simulation results show that the proposed method can get much better robot controllers than standard co-evolutionary algorithm.