外观
论文arXiv 2609.357091 个月前
使用离散 VLA 模型的人形机器人移动操作
原文链接：Humanoid Loco-Manipulation With Discrete VLA Model（arXiv 2609.35709 · 发布日期：2026-09-28）
Humanoid Loco-Manipulation With Discrete VLA Model
Holo-M面向人形机器人高维异构全身动作空间，采用统一动作分词与分组离散扩散解码，在SIMPLE基准验证并取得最高成功率。
核心要点
- 人形机器人的腿、躯干、手臂和手构成高维异构动作空间，带来分词、训练与实时推理挑战。
- Holo-M扩展语言模型词表加入动作token，并用统一动作分词器拆分端执行器、身体、手和运动学。
- 该模型可跨人形遥操作、自我中心人类视频和仿真等数据源训练，并用分组离散扩散满足实时控制。
- 在SIMPLE人形机器人移动操作基准的通用与专用评测中，Holo-M取得最高成功率，并将发布代码和权重。
验证范围与局限：验证范围为SIMPLE人形机器人移动操作基准的通用与专用评测。
英文摘要 (Abstract)
Vision-language-action (VLA) models using discrete action tokens have proven effective for controling robotic arms on manipulation tasks. For a humanoid, however, the whole-body action space -- legs, torso, arms, and hands -- is far higher-dimensional and heterogeneous, raising tokenization, training, and real-time inference challenges that the previous VLA models do not address. We present Holo-M, to our knowledge the first discrete VLA model for humanoid loco-manipulation that intrinsically exploits the language model by extending its vocabulary with action tokens. In this model, we devise a unified action tokenizer that decomposes the humanoid action space into four body-part-specific tokenizers -- end-effector, body, hand, and kinematics -- enabling training across drastically different embodiments and data sources, including humanoid teleoperation, ego-centric human video, and simulation. By extending the language model's vocabulary with these action tokens, we avoid the knowledge-insulation problem inherent to the models that use separate continuous action experts. To meet real-time control requirements, we decode each body part's action tokens through grouped discrete diffusion decoding, rather than using autoregression on the action tokens. We have conducted extensive experiments on the SIMPLE humanoid loco-manipulation benchmark, in which Holo-M achieves the highest success rates in both the generalist and specialist evaluations, leading the second best by significant margins. We will release all the code and model weights.
作者：Wenxin Shao, Siqi Chai, Kun Li, Kerou Zhang, Xinzhou Jiang, Wei Xu, Qiang Liu
来源
本页事实对应的公开页面，以原文为准。