Legs as Manipulator: Pushing Quadrupedal Agility
Beyond Locomotion

Xuxin Cheng1             Ashish Kumar2             Deepak Pathak1
1Carnegie Mellon University        2UC Berkeley          

Quadrupedal robot expands its capabilities by synthesizing agile locomotion and legged manipulation skills.

Abstract

Locomotion has seen dramatic progress for walking or running across challenging terrains. However, robotic quadrupeds are still far behind their biological counterparts, such as dogs, which display a variety of agile skills and can use the legs beyond locomotion to perform several basic manipulation tasks like interacting with objects and climbing. In this paper, we take a step towards bridging this gap by training quadruped robots not only to walk but also to use the front legs to climb walls, press buttons, and perform object interaction in the real world. To handle this challenging optimization, we decouple the skill learning broadly into locomotion, which involves anything that involves movement whether via walking or climbing a wall, and manipulation, which involves using one leg to interact while balancing on the other three legs. These skills are trained in simulation using curriculum and transferred to the real world using our proposed sim2real variant that builds upon recent locomotion success. Finally, we combine these skills into a robust long-term plan by learning a behavior tree that encodes a high-level task hierarchy from one clean expert demonstration. We evaluate our method in both simulation and real-world showing successful executions of both short as well as long-range tasks and how robustness helps confront external perturbations.




Project Video

Tasks without interruptions

The behavior tree is executed without any external interruptions/perturbations.


 

 

Tasks with interruptions

The behavior tree is executed with one specific interruptions/perturbations for each task. Our method is able to recover from the perturbation and continue the task.