Quadruped Robot Traversing 3D Complex Environments with Limited Perception

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. * Equal Contributions † corresponding author Research supported by the National Natural Science Foundation of China under grants No.92248304 and Shenzhen Science Fund for Distinguished Young Scholars under Grant RCJC20210706091946001 1 Tsinghua University, 100084 Beijing, China 2 University of Michigan, Ann Arbor, MI 48109, USA 3 Jianghuai Advanced Technology Center, 230000 Hefei, China 4 Shanghai University, 200444 Shanghai, China. This task is undeniably challenging. Our research finds that methods based on collision detection can enhance a robot’s per- ception 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. The videos and appendix can be found at Quad-Traverse-Go2.github.io