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. 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. The videos and appendix can be found at Quad-Traverse-Go2.github.io

Authors

• Yi Cheng
• Hang Liu
• Guoping Pan
• Houde Liu
• Linqi Ye

Keywords

• Training
• Three-dimensional displays
• Accuracy
• Computational modeling
• Propioception
• Sensors
• Quadrupedal robots
• Collision avoidance
• Robots
• Videos
• Complex Environment
• Quadruped Robot
• Simulation Experiments
• Real-world Experiments
• Collision Detection
• External Sensors
• Terrain
• Convolutional Neural Network
• Imagination
• 3D Space
• Simulation Environment
• Hip Joint
• Robotic Arm
• Linear Velocity
• Markov Decision Process
• Convolutional Neural Network Layers
• Linear Layer
• Potential Obstacles
• Real Robot
• Reward Mechanism
• Types Of Obstacles
• Front Foot
• State St
• Model-free Methods
• Single Time Step
• Linear Track
• Left Side
• Center Of Mass
• Privileged Information
• Record Length