A Species-based Approach to Brain-Body Co-Evolution of Modular Robots

Compared with fixed morphology robotic systems, self-reconfigurable modular (SRM) robots can reconfigure themselves to form a variety of morphologies, and carry on various types of motions. Recently, some co-evolutionary approaches have been proposed to co-evolve the robot morphology and associated controller simultaneously for locomotion tasks. However, these co-evolution approaches don't consider some physical limitations of SRM robots and usually request longer evolution process due to extensive searching space. To address these issues, we proposed a species-based co-evolution (S-CoE) algorithm. The S-CoE algorithm is applied on a simulated modular robot system and evaluated under two testing scenarios.