Quadruped robot traversing 3D complex environments with limited perception

TL;DR

This paper introduces an end-to-end learning-based quadruped robot controller that uses only proprioceptive sensors to detect and respond to collisions, enabling effective traversal of complex 3D environments without external sensors.

Contribution

The work presents a novel proprioception-only control method for quadruped robots, enhancing obstacle detection and traversal in complex environments compared to sensor-dependent approaches.

Findings

Successful real-world and simulation traversal of complex obstacles

Proprioception-based collision detection improves robustness

Enhanced environmental awareness without external sensors

Abstract

Traversing 3-D complex environments has always been a significant challenge for legged locomotion. Existing methods typically rely on external sensors such as vision and lidar to preemptively react to obstacles by acquiring environmental information. However, in scenarios like nighttime or dense forests, external sensors often fail to function properly, necessitating robots to rely on proprioceptive sensors to perceive diverse obstacles in the environment and respond promptly. This task is undeniably challenging. Our research finds that methods based on collision detection can enhance a robot's perception of environmental obstacles. In this work, we propose an end-to-end learning-based quadruped robot motion controller that relies solely on proprioceptive sensing. This controller can accurately detect, localize, and agilely respond to collisions in unknown and complex 3D environments, thereby improving the robot's traversability in complex environments. We demonstrate in both simulation and real-world experiments that our method enables quadruped robots to successfully traverse challenging obstacles in various complex environments.