ADAPT: Analytical Disturbance-Aware Policy Training for Humanoid Locomotion
2026-06-15 • Robotics
Robotics
AI summaryⓘ
The authors developed a new method called ADAPT to help humanoid robots better handle unexpected pushes and forces while moving. Instead of relying on extra sensors or complex learning tricks, their approach uses the robot's own physics model to estimate forces in real time. This helps the robot quickly understand and react to disturbances, making its walking more stable and accurate, even in new situations it hasn't seen before. Their tests showed that ADAPT outperforms traditional methods, improving balance and movement control without needing extra hardware.
humanoid robotsdisturbance observerforce/torque estimationlocomotion stabilityrobot dynamicsproprioceptiondomain randomizationout-of-distribution robustnessvelocity trackinganalytical modeling
Authors
Bofan Lyu, Jindou Jia, Kuangji Zuo, Yanshuo Lu, Shijia Han, Gen Li, Boyu Ma, Jingliang Li, Geng Li, Jianfei Yang
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.