Learning Stabilizing Control Policies for a Tensegrity Hopper with Augmented Random Search

摘要

In this paper, the authors consider a tensegrity hopper - a novel tensegrity-based robot, capable of moving by hopping. The paper focuses on the design of the stabilizing control policies, which are obtained with the Augmented Random Search method. In particular, the authors search for control policies, which allow the hopper to maintain vertical stability after performing a single jump. It is demonstrated, that the hopper can maintain a vertical configuration, subject to the different initial conditions and with changing control frequency rates. In particular, lowering control frequency from 1000Hz in training to 500Hz in execution does not affect the success rate of the balancing task.