aiqbench analysis
XHugWBC introduces a cross-embodiment training framework that enables a single policy to generalize across diverse humanoid robot designs with zero-shot transfer. By leveraging physics-consistent morphological randomization and semantically aligned observation spaces, the approach achieves robust control on both simulated and real-world robots without retraining for specific hardware. This advancement addresses a critical bottleneck in humanoid robotics by decoupling controller development from individual robot specifications.
Scalable and General Whole-Body Control for Cross-Humanoid Locomotion
arXiv:2602.05791v3 Announce Type: replace Abstract: 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.
Abstract: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.
Robotics (cs.RO)
arXiv:2602.05791 [cs.RO]
(or arXiv:2602.05791v3 [cs.RO] for this version)
Full text under the publisher's open licence · 162 words
Related coverage
HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning
arXiv · Jun 17, 2026
Towards a General Humanoid Loco-Manipulation Model via Egocentric Whole-Body Human Data Pretraining
arXiv · Oct 2, 2026
X-OP: Cross-Morphology Whole-Body Teleoperation via MPC Retargeting
arXiv · Jun 9, 2026
HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers
arXiv · Jun 9, 2026