Learning Plastic Matching of Robot Dynamics in Closed-loop Central Pattern Generators

18 July 2022

02:22

Ruppert, F., & Badri-Spröwitz, A. (2022). Learning Plastic Matching of Robot Dynamics in Closed-loop Central Pattern Generators. Nature Machine Intelligence. https://www.nature.com/articles/s42256-022-00505-4 Animals show agile locomotion performance with reduced control effort and energy efficiency by leveraging compliance in their muscles and tendons. However, it remains a question how biological locomotion controllers learn to leverage the intelligence embodied in their leg mechanics. Here we present a framework to match control patterns and mechanics based on the concept of short-term elasticity and long-term plasticity. Inspired by animals we design robot Morti with passive elastic legs. The quadruped is controlled by a bioinspired closed-loop central pattern generator that is designed to elastically mitigate short term perturbations using sparse contact feedback. By minimizing the amount of corrective feedback in the long term, the robot learns to match the controller to its mechanics and learns to walk within one hour. By leveraging the advantages of its mechanics, the robot improves its energy efficiency by 42% without explicit minimization in the cost function.