Robust Agility via Learned Zero Dynamics Policies

TL;DR

This paper introduces Zero Dynamics Policies, a novel control framework for hybrid underactuated systems that enhances robustness and agility by leveraging invariant mappings and reducing online computation.

Contribution

It presents a new control design method that exploits system structure to improve stability, robustness, and computational efficiency in hybrid underactuated systems.

Findings

Successfully stabilizes hybrid underactuated systems

Demonstrates robustness over 3000 hops on rough terrain

Reduces online computational overhead significantly

Abstract

We study the design of robust and agile controllers for hybrid underactuated systems. Our approach breaks down the task of creating a stabilizing controller into: 1) learning a mapping that is invariant under optimal control, and 2) driving the actuated coordinates to the output of that mapping. This approach, termed Zero Dynamics Policies, exploits the structure of underactuation by restricting the inputs of the target mapping to the subset of degrees of freedom that cannot be directly actuated, thereby achieving significant dimension reduction. Furthermore, we retain the stability and constraint satisfaction of optimal control while reducing the online computational overhead. We prove that controllers of this type stabilize hybrid underactuated systems and experimentally validate our approach on the 3D hopping platform, ARCHER. Over the course of 3000 hops the proposed framework demonstrates robust agility, maintaining stable hopping while rejecting disturbances on rough terrain.