VOFA: Visual Object Goal Pushing with Force-Adaptive Control for Humanoids
Zichao Hu, Zifan Xu, Dongsik Chang, He Yin, Linh Tran, Roberto Mart\'in-Mart\'in, Peter Stone, Jingyu Qiao, Joydeep Biswas

TL;DR
VOFA is a hierarchical humanoid robot system that robustly pushes objects with unknown properties to goal positions using onboard perception and force-adaptive control, achieving high success rates in simulation and real-world tests.
Contribution
The paper introduces VOFA, a novel visual goal-conditioned humanoid pushing system with a two-level architecture combining visuomotor policy and force-adaptive control, capable of handling unknown object properties.
Findings
Over 90% success in simulation
Over 80% success in real-world trials
Pushes objects up to 17kg, exceeding half of robot's weight
Abstract
The ability to push large objects in a goal-directed manner using onboard egocentric perception is an essential skill for humanoid robots to perform complex tasks such as material handling in warehouses. To robustly manipulate heavy objects to arbitrary goal configurations, the robot must cope with unknown object mass and ground friction, noisy onboard perception, and actuation errors; all in a real-time feedback loop. Existing solutions either rely on privileged object-state information without onboard perception or lack robustness to variations in goal configurations and object physical properties. In this work, we present VOFA, a visual goal-conditioned humanoid loco-manipulation system capable of pushing objects with unknown physical properties to arbitrary goal positions. VOFA consists of a two-level hierarchical architecture with a high-level visuomotor policy and a low-level…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
