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.
Weitere Kapitel dieses Buchs durch Wischen aufrufen
- Generating Smart Robot Controllers Through Co-evolution
- Springer Berlin Heidelberg