CapPlanner: Adaptable to Various Topology and Locomotion Capability for Hexapod Robots

Hexapod robots are good at traversing on complex terrains, yet its capability is challenging to define. The robot's traverse ability varies due to its structure, topology, and locomotion controller. The existing motion planner rarely considers the robot's traverse ability, causing higher failure risk when it gives motion commands that do not match the robot's capability. In this paper, we present CapPlanner, a hierarchical motion control and planning system which can do long-range locomotion control and planning according to the learned traverse capability of the robot in different topologies. It consists of two layers, the bottom-level controller computes the trajectory of the body and the feet according to the terrain, local target and current feets' positions. Besides, it controls the motors to track the calculated trajectory. The top-level controller learns the traverse ability of the robot with its bottom-level controller by simulating locomotion tasks on various terrains and in different topologies. Hence our CapPlanner can guide the robot to reach a long-term destination with a much higher success rate. In the experiment, we test CapPlanner in simulation and on our real hexapod robot, Qingzhui. The results show that CapPlanner is able to accomplish long distance and tough terrain locomotion planning for hexapod robot.