SLR: Learning Quadruped Locomotion without Privileged Information

TL;DR

This paper introduces SLR, a novel reinforcement learning approach for quadruped robots that learns control policies without relying on privileged information, outperforming existing methods with limited proprioceptive data.

Contribution

SLR is the first method to achieve high-performance quadruped locomotion without privileged information, using self-learning of latent representations.

Findings

SLR outperforms state-of-the-art algorithms on benchmark tasks.

SLR enables quadrupeds to traverse challenging terrains.

The method requires only proprioceptive data for training.

Abstract

The recent mainstream reinforcement learning control for quadruped robots often relies on privileged information, demanding meticulous selection and precise estimation, thereby imposing constraints on the development process. This work proposes a Self-learning Latent Representation (SLR) method, which achieves high-performance control policy learning without the need for privileged information. To enhance the credibility of the proposed method's evaluation, SLR was directly compared with state-of-the-art algorithms using their open-source code repositories and original configuration parameters. Remarkably, SLR surpasses the performance of previous methods using only limited proprioceptive data, demonstrating significant potential for future applications. Ultimately, the trained policy and encoder empower the quadruped robot to traverse various challenging terrains. Videos of our results can be found on our website: https://11chens.github.io/SLR/