aiqbench analysis
This research advances humanoid robot stability by integrating learned models of Center of Pressure dynamics to optimize reactive hand contacts during disturbances. The approach significantly outperforms traditional optimization methods and baseline strategies in simulation and hardware trials, demonstrating faster recovery times and higher impulse resilience. By enabling rapid evaluation of bracing points, this method addresses a critical safety gap for humanoids operating in unstructured environments where foot-only contact is insufficient.
Reactive Humanoid Multi-Contact Using Learned Stability Models
arXiv:2610.00823v1 Announce Type: new Abstract: We present a planning and control approach to reactively use hand contacts to stabilize a humanoid in low stability scenarios, where only using feet contacts may result in a fall. Candidate contacts are sampled within the robot's reachable workspace, and a preview is computed by rolling out the centroidal dynamics through pre-impact, impact and post-impact phases. Sampled points are scored based on the Center of Pressure (CoP) control authority at the post-impact phase. Central to our approach is a learned model of the robot's CoP region during post-impact, which enables rapid evaluation of candidate contact points compared to traditional optimization-based methods. The presented planner has two stages: the first selects an optimal bracing region and the second computes an optimal bracing point within the region. Our simulation results demonstrate an average increase in impulse resilience of 89% over recovery without hand contacts and 17% over a naive planning strategy (closest reachable region). We validate our framework on hardware, performing push tests while standing and walking. The standing trials show an average 43% reduction in stabilization time compared to naive hand placement and the walking trials demonstrate a 18% reduction compared to baseline recovery (without hand contacts).
Abstract:We present a planning and control approach to reactively use hand contacts to stabilize a humanoid in low stability scenarios, where only using feet contacts may result in a fall. Candidate contacts are sampled within the robot's reachable workspace, and a preview is computed by rolling out the centroidal dynamics through pre-impact, impact and post-impact phases. Sampled points are scored based on the Center of Pressure (CoP) control authority at the post-impact phase. Central to our approach is a learned model of the robot's CoP region during post-impact, which enables rapid evaluation of candidate contact points compared to traditional optimization-based methods. The presented planner has two stages: the first selects an optimal bracing region and the second computes an optimal bracing point within the region. Our simulation results demonstrate an average increase in impulse resilience of 89% over recovery without hand contacts and 17% over a naive planning strategy (closest reachable region). We validate our framework on hardware, performing push tests while standing and walking. The standing trials show an average 43% reduction in stabilization time compared to naive hand placement and the walking trials demonstrate a 18% reduction compared to baseline recovery (without hand contacts).
Robotics (cs.RO)
arXiv:2610.00823 [cs.RO]
(or arXiv:2610.00823v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.00823 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 289 words
Related coverage
DreamMimic: Learning Visuomotor Whole-Body Loco-Manipulation via World Model
arXiv · Aug 25, 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · May 21, 2026
ForeTac-VLA: A Forecasting-Based Tactile-Vision-Language-Action Model for Contact-Rich Robotic Manipulation
arXiv · Sep 21, 2026
A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying Forces
arXiv · Aug 5, 2026