Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Visual Whole-Body Control for Legged Loco-Manipulation

About

We study the problem of mobile manipulation using legged robots equipped with an arm, namely legged loco-manipulation. The robot legs, while usually utilized for mobility, offer an opportunity to amplify the manipulation capabilities by conducting whole-body control. That is, the robot can control the legs and the arm at the same time to extend its workspace. We propose a framework that can conduct the whole-body control autonomously with visual observations. Our approach, namely Visual Whole-Body Control(VBC), is composed of a low-level policy using all degrees of freedom to track the body velocities along with the end-effector position, and a high-level policy proposing the velocities and end-effector position based on visual inputs. We train both levels of policies in simulation and perform Sim2Real transfer for real robot deployment. We perform extensive experiments and show significant improvements over baselines in picking up diverse objects in different configurations (heights, locations, orientations) and environments.

Minghuan Liu, Zixuan Chen, Xuxin Cheng, Yandong Ji, Ri-Zhao Qiu, Ruihan Yang, Xiaolong Wang• 2024

Related benchmarks

TaskDatasetResultRank
Pick-&-PlaceSix Evaluation Scenarios Simulation
Success Rate80
7
Pick-&-PlaceSix Evaluation Scenarios Real-world
Success Rate30
7
Loco-manipulationSimple Terrain Simulation
Velocity Error (Vw)0.865
3
Showing 3 of 3 rows

Other info

Follow for update