aiqbench analysis
ADAPT introduces a physically grounded disturbance observer that enhances humanoid robot stability without relying on external force sensors. By integrating real-time torque estimates directly into the policy, this framework significantly improves robustness against unexpected pushes and asymmetric payloads in dynamic environments. This advancement addresses critical challenges for deploying humanoids safely within complex, interactive settings where maintaining balance under physical contact is essential.
ADAPT: Analytical Disturbance-Aware Policy Training for Humanoid Locomotion
arXiv:2606.16542v1 Announce Type: new Abstract: Humanoids deployed in human-centered environments must handle force-interactive tasks, where external contacts introduce unexpected disturbances that disrupt locomotion accuracy and stability. Existing learning-based approaches rely on broad domain randomization, task-specific force objectives, or learning-based force estimators from motion history, each of which compromises accuracy, task transferability, or out-of-distribution (OOD) robustness. We present Analytical Disturbance-Aware Policy Training (ADAPT), a framework that equips humanoid policies with a physically grounded disturbance observer. The core of ADAPT is an analytical whole-body disturbance observer that estimates residual force/torque online with the accessible robot dynamics, without requiring force/torque sensors. Fed directly into the policy, the estimated disturbances give the humanoid an explicit, physics-derived sense of external force/torque that can generalize across diverse unseen scenes. Experiments on a Unitree G1 humanoid show that ADAPT achieves accurate disturbance prediction and stronger robustness than a proprioception-only baseline under torso perturbations, standing pushes, and asymmetric hand payloads, with improved velocity tracking even on OOD disturbances. Moreover, ADAPT enables penalizing inferred disturbances at lower-body joints to encourage lighter locomotion.
Abstract:Humanoids deployed in human-centered environments must handle force-interactive tasks, where external contacts introduce unexpected disturbances that disrupt locomotion accuracy and stability. Existing learning-based approaches rely on broad domain randomization, task-specific force objectives, or learning-based force estimators from motion history, each of which compromises accuracy, task transferability, or out-of-distribution (OOD) robustness. We present Analytical Disturbance-Aware Policy Training (ADAPT), a framework that equips humanoid policies with a physically grounded disturbance observer. The core of ADAPT is an analytical whole-body disturbance observer that estimates residual force/torque online with the accessible robot dynamics, without requiring force/torque sensors. Fed directly into the policy, the estimated disturbances give the humanoid an explicit, physics-derived sense of external force/torque that can generalize across diverse unseen scenes. Experiments on a Unitree G1 humanoid show that ADAPT achieves accurate disturbance prediction and stronger robustness than a proprioception-only baseline under torso perturbations, standing pushes, and asymmetric hand payloads, with improved velocity tracking even on OOD disturbances. Moreover, ADAPT enables penalizing inferred disturbances at lower-body joints to encourage lighter locomotion.
Robotics (cs.RO)
arXiv:2606.16542 [cs.RO]
(or arXiv:2606.16542v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.16542 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 · 261 words
Related coverage
CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation
arXiv · Jun 4, 2026
TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
arXiv · Sep 28, 2026
TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
arXiv · Jun 5, 2026
CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation
arXiv · Jun 16, 2026