DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learning

TL;DR

This paper introduces DreamWaQ++, a multi-modal reinforcement learning approach that fuses proprioception and exteroception to enable quadrupedal robots to navigate complex, real-world environments resiliently and safely.

Contribution

It presents a novel multi-modal reinforcement learning framework that enhances quadrupedal locomotion robustness by integrating proprioceptive and exteroceptive data.

Findings

Achieves agile locomotion on rough terrains and stairs

Demonstrates robustness against out-of-distribution scenarios

Outperforms previous methods in complex environments

Abstract

Quadrupedal robots hold promising potential for applications in navigating cluttered environments with resilience akin to their animal counterparts. However, their floating base configuration makes them vulnerable to real-world uncertainties, yielding substantial challenges in their locomotion control. Deep reinforcement learning has become one of the plausible alternatives for realizing a robust locomotion controller. However, the approaches that rely solely on proprioception sacrifice collision-free locomotion because they require front-feet contact to detect the presence of stairs to adapt the locomotion gait. Meanwhile, incorporating exteroception necessitates a precisely modeled map observed by exteroceptive sensors over a period of time. Therefore, this work proposes a novel method to fuse proprioception and exteroception featuring a resilient multi-modal reinforcement learning. The proposed method yields a controller that showcases agile locomotion performance on a quadrupedal robot over a myriad of real-world courses, including rough terrains, steep slopes, and high-rise stairs, while retaining its robustness against out-of-distribution situations.