Scalable and General Whole-Body Control for Cross-Humanoid Locomotion
This work addresses the problem of robot-specific training in humanoid control, enabling a generalist controller that can be deployed across different hardware without retraining.
XHugWBC enables a single whole-body control policy to generalize across diverse humanoid robots with one-time training, achieving zero-shot transfer to unseen robots. Experiments on 12 simulated and 7 real-world humanoids demonstrate strong generalization and robustness.
Learning-based whole-body controllers have become a key driver for humanoid robots, yet most existing approaches require robot-specific training. In this paper, we study the problem of cross-embodiment humanoid control and show that a single policy can robustly generalize across a wide range of humanoid robot designs with one-time training. We introduce XHugWBC, a novel cross-embodiment training framework that enables generalist humanoid control through: (1) physics-consistent morphological randomization, (2) semantically aligned observation and action spaces across diverse humanoid robots, and (3) effective policy architectures modeling morphological and dynamical properties. XHugWBC is not tied to any specific robot. Instead, it internalizes a broad distribution of morphological and dynamical characteristics during training. By learning motion priors from diverse randomized embodiments, the policy acquires a strong structural bias that supports zero-shot transfer to previously unseen robots. Experiments on twelve simulated humanoids and seven real-world robots demonstrate the strong generalization and robustness of the resulting universal controller.