Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jia, Haozhe, Jin, Honglei, Zhang, Yuan, Fan, Youcheng, Liang, Shaofeng, Wang, Lei, Jin, Shuxu, Yu, Kuimou, Zhang, Zinuo, Song, Jianfei, Chen, Wenshuo, Yue, Yutao
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.14417
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913147098497024
author Jia, Haozhe
Jin, Honglei
Zhang, Yuan
Fan, Youcheng
Liang, Shaofeng
Wang, Lei
Jin, Shuxu
Yu, Kuimou
Zhang, Zinuo
Song, Jianfei
Chen, Wenshuo
Yue, Yutao
author_facet Jia, Haozhe
Jin, Honglei
Zhang, Yuan
Fan, Youcheng
Liang, Shaofeng
Wang, Lei
Jin, Shuxu
Yu, Kuimou
Zhang, Zinuo
Song, Jianfei
Chen, Wenshuo
Yue, Yutao
contents Natural language is an intuitive interface for humanoid robots, yet streaming whole-body control requires control representations that are executable now and anticipatory of future physical transitions. Existing language-conditioned humanoid systems typically generate kinematic references that a low-level tracker must repair reactively, or use latent/action policies whose outputs do not explicitly encode upcoming contact changes, support transfers, and balance preparation. We propose \textbf{DAJI} (\emph{Dynamics-Aligned Joint Intent}), a hierarchical framework that learns an anticipatory joint-intent interface between language generation and closed-loop control. DAJI-Act distills a future-aware teacher into a deployable diffusion action policy through student-driven rollouts, while DAJI-Flow autoregressively generates future intent chunks from language and intent history. Experiments show that DAJI achieves strong results in anticipatory latent learning, single-instruction generation, and streaming instruction following, reaching 94.42\% rollout success on HumanML3D-style generation and 0.152 subsequence FID on BABEL.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14417
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control
Jia, Haozhe
Jin, Honglei
Zhang, Yuan
Fan, Youcheng
Liang, Shaofeng
Wang, Lei
Jin, Shuxu
Yu, Kuimou
Zhang, Zinuo
Song, Jianfei
Chen, Wenshuo
Yue, Yutao
Robotics
Computer Vision and Pattern Recognition
Natural language is an intuitive interface for humanoid robots, yet streaming whole-body control requires control representations that are executable now and anticipatory of future physical transitions. Existing language-conditioned humanoid systems typically generate kinematic references that a low-level tracker must repair reactively, or use latent/action policies whose outputs do not explicitly encode upcoming contact changes, support transfers, and balance preparation. We propose \textbf{DAJI} (\emph{Dynamics-Aligned Joint Intent}), a hierarchical framework that learns an anticipatory joint-intent interface between language generation and closed-loop control. DAJI-Act distills a future-aware teacher into a deployable diffusion action policy through student-driven rollouts, while DAJI-Flow autoregressively generates future intent chunks from language and intent history. Experiments show that DAJI achieves strong results in anticipatory latent learning, single-instruction generation, and streaming instruction following, reaching 94.42\% rollout success on HumanML3D-style generation and 0.152 subsequence FID on BABEL.
title Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.14417