Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Abstract

Figure 1: Main hypothesis: In the brain-body co-optimization of soft robots, the locomotion performance of modular controllers is significantly more robust than global controllers to perturbations of their robot's morphology. This allows better transfer of that controller to a robot's offspring with morphological mutations. This increases the rate of successful morphological mutations during the co-optimization process and leads to a more efficient and effective search over robot designs.