{"ID":2837634,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.19236","arxiv_id":"2511.19236","title":"SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Control","abstract":"Existing humanoid control systems often rely on teleoperation or modular generation pipelines that separate language understanding from physical execution. However, the former is entirely human-driven, and the latter lacks tight alignment between language commands and physical behaviors. In this paper, we present SENTINEL, a fully end-to-end language-action model for humanoid whole-body control. We construct a large-scale dataset by tracking human motions in simulation using a pretrained whole body controller, combined with their text annotations. The model directly maps language commands and proprioceptive inputs to low-level actions without any intermediate representation. The model generates action chunks using flow matching, which can be subsequently refined by a residual action head for real-world deployment. Our method exhibits strong semantic understanding and stable execution on humanoid robots in both simulation and real-world deployment, and also supports multi-modal extensions by converting inputs into texts.","short_abstract":"Existing humanoid control systems often rely on teleoperation or modular generation pipelines that separate language understanding from physical execution. However, the former is entirely human-driven, and the latter lacks tight alignment between language commands and physical behaviors. In this paper, we present SENTI...","url_abs":"https://arxiv.org/abs/2511.19236","url_pdf":"https://arxiv.org/pdf/2511.19236v1","authors":"[\"Yuxuan Wang\",\"Haobin Jiang\",\"Shiqing Yao\",\"Ziluo Ding\",\"Zongqing Lu\"]","published":"2025-11-24T15:48:59Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[]","has_code":false}