Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomization

TL;DR

This paper introduces a simple random force injection method during training to improve the robustness of locomotion policies, enabling effective sim-to-real transfer across different quadrupedal robots and terrains.

Contribution

The study proposes random force injection (RFI) and its extension ERFI as novel, minimalistic approaches to enhance policy robustness without extensive system identification or domain adaptation.

Findings

ERFI improves robustness to system mass variations by 53%.

Policies trained with RFI/ERFI transfer successfully to real robots.

ERFI enables robust locomotion over uneven outdoor terrain.

Abstract

Training deep reinforcement learning (DRL) locomotion policies often require massive amounts of data to converge to the desired behaviour. In this regard, simulators provide a cheap and abundant source. For successful sim-to-real transfer, exhaustively engineered approaches such as system identification, dynamics randomization, and domain adaptation are generally employed. As an alternative, we investigate a simple strategy of random force injection (RFI) to perturb system dynamics during training. We show that the application of random forces enables us to emulate dynamics randomization. This allows us to obtain locomotion policies that are robust to variations in system dynamics. We further extend RFI, referred to as extended random force injection (ERFI), by introducing an episodic actuation offset. We demonstrate that ERFI provides additional robustness for variations in system mass offering on average a 53% improved performance over RFI. We also show that ERFI is sufficient to perform a successful sim-to-real transfer on two different quadrupedal platforms, ANYmal C and Unitree A1, even for perceptive locomotion over uneven terrain in outdoor environments.