Visual Manipulation with Legs

Xialin He, Chengjing Yuan, Wenxuan Zhou, Ruihan Yang, David Held, Xiaolong Wang

Keywords: Legged robots, Non-prehensile manipulation, Reinforcement Learning

TL;DR: This work presents a system that empowers quadruped robot to perform object interactions with its legs

Abstract: Animals have the ability to use their arms and legs for both locomotion and manipulation. We envision quadruped robots to have the same versatility. This work presents a system that empowers a quadruped robot to perform object interactions with its legs, drawing inspiration from non-prehensile manipulation techniques. The proposed system has two main components: a visual manipulation policy module and a loco-manipulator module. The visual manipulation policy module decides how the leg should interact with the object, trained with reinforcement learning (RL) with point cloud observations and object-centric actions. The loco-manipulator controller controls the leg movements and body pose adjustments, implemented based on impedance control and Model Predictive Control (MPC). Besides manipulating objects with a single leg, the proposed system can also select from left or right legs based on the critic maps and move the object to distant goals through robot base adjustment. In the experiments, we evaluate the proposed system with the object pose alignment tasks both in simulation and in the real world, demonstrating object manipulation skills with legs more versatile than previous work.

Website: https://legged-manipulation.github.io/

Student Paper: yes

Submission Number: 44