Adaptation as a more powerful tool than decomposition and integration: experimental evidences from evolutionary robotics

A new way of building control systems, known as behavior based robotics, has been proposed to overcome the difficulties of the traditional Al approach to robotics. Most of the work done in behavior-based robotics involves a decomposition process (in which the behavior required is broken down into simpler sub-components) and an integration process (in which the modules designed to produce the sub-behaviors are put together). We claim that decomposition and integration should be the result of an adaptation process and not of the decision of the experimenter. In this paper we support this hypothesis by showing how in two different cases a more simple and robust solution can be obtained by letting the entire behavior emerge through an evolutionary technique than by trying to design a set of modules and to coordinate them.