Zhaohui Yang, Quanbao Lin, Chengqi Shi, Zhenglang Weng, Jicheng Lin, Boyu Chen, Tengjie Zhu, Guanzhu Ren, Jiahao Xu, Yang Feng, Xiaokang Yang, Yao Mu · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.30044 · cited by 0 works (OpenAlex) · open-access PDF
La loco-manipulation humaine nécessite une interface efficace entre les politiques de tâches de haut niveau et le contrôle du corps entier. Les interfaces existantes s'appuient généralement sur une représentation d'action unique pour l'intention de la tâche et la coordination du corps entier. Cela peut peser sur la politique de haut niveau ou laisser un aspect sous-spécifié. Nous présentons SP-HLM, un cadre construit sur une interface basse-position. L'interface combine cinq poses de corps critiques de tâches avec un mouvement latent appris avant de représenter l'intention spatiale et la coordination du corps en formes complémentaires. SP-VLA, un modèle d'action de langue de vision, prédit d'abord les poses sparse pertinentes et les positions articulaires
Machine translation (Meta M2M100); the English original follows.
Humanoid loco-manipulation requires an effective interface between high-level task policies and whole-body control. Existing interfaces typically rely on a single action representation for both task intent and whole-body coordination. This may burden the high-level policy or leave one aspect underspecified. We present SP-HLM, a framework built on a sparse-pose-driven interface. The interface combines five task-critical body poses with a learned latent motion prior to represent spatial intent and whole-body coordination in complementary forms. SP-VLA, a vision-language-action model, first predicts task-relevant sparse poses and finger joint positions from multimodal observations and language instructions using asynchronous action-chunk inference. Given these sparse targets, SP-MGM, a motion generation model trained through two-stage distillation, reconstructs coordinated full-body motion in real time. A pretrained motion encoder maps this motion to a compact latent representation. SP-GMT, a general motion tracker, then integrates the explicit sparse targets with this implicit motion prior for whole-body control. Experiments in simulation and on a real humanoid robot demonstrate improved motion tracking, whole-body coordination, and loco-manipulation success over existing approaches. Additional results and videos are available on our \href{https://sp-hlm.github.io/}{\textcolor{blue}{project page}}.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Humanoid robot, Motion (physics), Computer science, Artificial intelligence, Task (project management), Computer vision
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30044, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange