ADP: Adversarial Dynamics Priors for Physically Grounded Humanoid Locomotion
arXiv:2607.03454
The paper introduces Adversarial Dynamics Priors (ADP), a method that uses adversarial training on dynamics features such as center‑of‑mass motion and contact forces to make humanoid walking controllers more robust to external perturbations.
Abstract
In this paper, we propose Adversarial Dynamics Priors (ADP) for perturbation-resilient humanoid locomotion control. Existing motion prior-based methods induce natural motion styles by imitating kinematic motion features, but they do not directly regularize dynamics features, such as CoM motion, centroidal momentum, contact forces, and contact states. To address this limitation, we replace kinematic motion-style feature with selected dynamics features extracted from locomotion trajectories as the target of adversarial regularization. To this end, we use trajectory optimization to construct a reference dataset and train a discriminator to evaluate whether policy-induced temporal windows are consistent with the resulting reference distribution. Without explicit motion tracking, ADP encourages policy rollouts to remain close to the reference support, even after perturbations. Experimental results show that, compared with AMP, the strongest baseline in our evaluation, ADP improves the -success impulse threshold () by , while reducing direction-averaged recovery time and velocity tracking error by and , respectively.
8 pages, 6 figures