Guardado en:
Detalles Bibliográficos
Autores principales: Bai, Shuanghao, Li, Meng, Lv, Xinyuan, Wang, Jiawei, Wang, Xinhua, Liao, Fei, Hou, Chengkai, Gu, Langzhe, Zhou, Wanqi, Wu, Kun, Ding, Ziluo, Xu, Zhiyuan, Sun, Lei, Zhang, Shanghang, Che, Zhengping, Tang, Jian, Chen, Badong
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.07993
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914580099235840
author Bai, Shuanghao
Li, Meng
Lv, Xinyuan
Wang, Jiawei
Wang, Xinhua
Liao, Fei
Hou, Chengkai
Gu, Langzhe
Zhou, Wanqi
Wu, Kun
Ding, Ziluo
Xu, Zhiyuan
Sun, Lei
Zhang, Shanghang
Che, Zhengping
Tang, Jian
Chen, Badong
author_facet Bai, Shuanghao
Li, Meng
Lv, Xinyuan
Wang, Jiawei
Wang, Xinhua
Liao, Fei
Hou, Chengkai
Gu, Langzhe
Zhou, Wanqi
Wu, Kun
Ding, Ziluo
Xu, Zhiyuan
Sun, Lei
Zhang, Shanghang
Che, Zhengping
Tang, Jian
Chen, Badong
contents Humans achieve complex manipulation through coordinated whole-body control, whereas most Vision-Language-Action (VLA) models treat robot body parts largely independently, making high-DoF humanoid control challenging and often unstable. We present HEX, a state-centric framework for coordinated manipulation on full-sized bipedal humanoid robots. HEX introduces a humanoid-aligned universal state representation for scalable learning across heterogeneous embodiments, and incorporates a Mixture-of-Experts Unified Proprioceptive Predictor to model whole-body coordination and temporal motion dynamics from large-scale multi-embodiment trajectory data. To efficiently capture temporal visual context, HEX uses lightweight history tokens to summarize past observations, avoiding repeated encoding of historical images during inference. It further employs a residual-gated fusion mechanism with a flow-matching action head to adaptively integrate visual-language cues with proprioceptive dynamics for action generation. Experiments on real-world humanoid manipulation tasks show that HEX achieves state-of-the-art performance in task success rate and generalization, particularly in fast-reaction and long-horizon scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2604_07993
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation
Bai, Shuanghao
Li, Meng
Lv, Xinyuan
Wang, Jiawei
Wang, Xinhua
Liao, Fei
Hou, Chengkai
Gu, Langzhe
Zhou, Wanqi
Wu, Kun
Ding, Ziluo
Xu, Zhiyuan
Sun, Lei
Zhang, Shanghang
Che, Zhengping
Tang, Jian
Chen, Badong
Robotics
Humans achieve complex manipulation through coordinated whole-body control, whereas most Vision-Language-Action (VLA) models treat robot body parts largely independently, making high-DoF humanoid control challenging and often unstable. We present HEX, a state-centric framework for coordinated manipulation on full-sized bipedal humanoid robots. HEX introduces a humanoid-aligned universal state representation for scalable learning across heterogeneous embodiments, and incorporates a Mixture-of-Experts Unified Proprioceptive Predictor to model whole-body coordination and temporal motion dynamics from large-scale multi-embodiment trajectory data. To efficiently capture temporal visual context, HEX uses lightweight history tokens to summarize past observations, avoiding repeated encoding of historical images during inference. It further employs a residual-gated fusion mechanism with a flow-matching action head to adaptively integrate visual-language cues with proprioceptive dynamics for action generation. Experiments on real-world humanoid manipulation tasks show that HEX achieves state-of-the-art performance in task success rate and generalization, particularly in fast-reaction and long-horizon scenarios.
title HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation
topic Robotics
url https://arxiv.org/abs/2604.07993