Exploring Behaviors of Caterpillar-Like Soft Robots with a Central Pattern Generator-Based Controller and Reinforcement Learning.

Due to their flexibility, soft-bodied robots can potentially achieve rich and various behaviors within a single body. However, to date, no methodology has effectively harnessed these robots to achieve such diverse desired functionalities. Controllers that accomplish only a limited range of behaviors in such robots have been handcrafted. Moreover, the behaviors of these robots should be determined through body-environment interactions because an appropriate behavior may not always be manifested even if the body dynamics are given. Therefore, we have proposed SenseCPG-PGPE, a method for automatically designing behaviors for caterpillar-like soft-bodied robots. This method optimizes mechanosensory feedback to a central pattern generator (CPG)-based controller, which controls actuators in a robot, using policy gradients with parameter-based exploration (PGPE). In this article, we deeply investigated this method. We found that PGPE can optimize a CPG-based controller for soft-bodied robots that exhibit viscoelasticity and large deformation, whereas other popular policy gradient methods, such as trust region policy optimization and proximal policy optimization, cannot. Scalability of the method was confirmed using simulation as well. Although SenseCPG-PGPE uses a CPG-based controller, it can achieve nonsteady motion such as climbing a step in a simulated robot. The approach also resulted in distinctive behaviors depending on different body-environment conditions. These results demonstrate that the proposed method enables soft robots to explore a variety of behaviors automatically.