Planning of diverse complex cooperative robot actions using Multi-stage Genetic Algorithm

Abstract

This article is concerned with autonomous planning of diverse cooperative robot actions. In this work complex cooperative actions are realized based upon the intelligent composite motion control, which is a learning methodology for intelligent robots that gradually realize complex actions from fundamental motions. For efficient construction of action intelligence multi-stage genetic algorithm, MGA, is used. The MGA solves a large scale optimization problem with complicated constraints as multi-stage but small scale combinatorial optimization problems with simple constraints, which are solved by GA to generate their suboptimal solution sets. In order to realize autonomous planning of diverse cooperation according to situation, variable-chromosome-length genetic algorithm (VGA) is introduced and combined to MGA. The presented method is successfully applied to planning of diverse cooperative robot soccer actions according to situation.