analiza aiqbench
This research introduces the Supporting Hand Strategy (SHS), a reinforcement-learning approach that allows humanoid robots to brace against environments with one hand while applying significantly higher forces with the other. Tested on the Unitree G1, the method triples sustainable contact force from 13.5 N to 60 N without requiring human motion data or online trajectory planning. The technique demonstrates strong generalization across different task regions, offering a scalable solution for improving whole-body stability during forceful manipulation.
Brace Yourself: Task-Conditioned Environmental Bracing for Forceful Humanoid Manipulation
arXiv:2609.25486v1 Announce Type: new Abstract: Forceful manipulation is challenging for humanoid robots because interaction forces can disturb whole-body balance. We introduce the Supporting Hand Strategy (SHS), which enables a humanoid to brace against the environment with one hand while performing forceful manipulation with the other. SHS optimises a task-conditioned support configuration that guides two synchronous reinforcement-learning policies, without human motion data or online whole-body trajectory planning. On a Unitree G1, SHS achieved usable contact forces up to 60 N, compared with a maximum sustained force of 13.5 N without environmental bracing, while substantially improving force tracking over a task-independent support configuration. The same policies generalised to different task regions without retraining. SHS therefore provides a simple mechanism for substantially extending humanoid forceful-manipulation capability.
Abstract:Forceful manipulation is challenging for humanoid robots because interaction forces can disturb whole-body balance. We introduce the Supporting Hand Strategy (SHS), which enables a humanoid to brace against the environment with one hand while performing forceful manipulation with the other. SHS optimises a task-conditioned support configuration that guides two synchronous reinforcement-learning policies, without human motion data or online whole-body trajectory planning. On a Unitree G1, SHS achieved usable contact forces up to 60 N, compared with a maximum sustained force of 13.5 N without environmental bracing, while substantially improving force tracking over a task-independent support configuration. The same policies generalised to different task regions without retraining. SHS therefore provides a simple mechanism for substantially extending humanoid forceful-manipulation capability.
Submitted to IEEE Robotics and Automation Letters (RA-L). 8 pages, 6 figures. Video demonstration: this https URL. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
Robotics (cs.RO)
arXiv:2609.25486 [cs.RO]
(or arXiv:2609.25486v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.25486 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 178 cuvinte
Subiecte conexe

How to Evaluate General-Purpose Robot Policies for Real-World Deployment
NVIDIA · 12 iul. 2026

News
Quantum Computing Report · 7 iun. 2026

Forbes Asia 100 To Watch 2026
forbes.com · 24 aug. 2026
Opt2VLA: Force-Aware Vision-Language-Action for Contact-Rich Humanoid Whole-Body Manipulation
arXiv · 22 sept. 2026