外观
论文arXiv 2504.095322025-04-13
Humanoid-COA框架实现人形机器人零样本移动操作
提出Humanoid-COA框架，通过具身动作链机制将多模态大模型推理转化为结构化动作序列，在Unitree H1-2与G1上实现零样本移动操作，显著优于现有基线并支持长程非结构化任务。
宇树 H1本文由 AI 根据公开内容整理，可能有误，请以原文为准：Humanoid Agent via Embodied Chain-of-Action Reasoning with Multimodal Foundation Models for Zero-Shot Loco-Manipulation（arXiv 2504.09532）
核心内容
针对人形机器人移动操作中指令理解与全身协调难题，研究团队提出Humanoid-COA框架，首次将基础模型推理与具身动作链（CoA）机制结合以实现零样本loco-manipulation。该工作在Unitree H1-2和G1两款人形机器人上完成验证，在开放测试区及公寓环境中，于纯操作、纯移动及复合任务中均大幅超越先前基线，展现出对长时序与非结构化场景的强泛化能力。
技术方案核心在于感知-推理-行动范式中的推理阶段：CoA机制通过可供性分析、空间推理与全身动作推理，将高层自然语言指令分解为结构化的移动与操作原语序列。系统利用多模态基础模型提供可迁移表征，解决了以往方法仅能孤立处理移动或操作的局限，使机器人能在无额外训练数据的情况下，依据语义理解自主规划并执行复杂的全身协同动作序列。
关键看点
- 具身动作链：通过可供性与空间推理将自然语言指令解耦为结构化移动与操作原语序列
- 零样本泛化：无需任务特定微调即可在公寓等非结构化环境执行长程复合任务
- 双机型验证：在Unitree H1-2与G1平台上实测，综合性能显著优于现有移动操作基线
- 全身协同推理：集成多模态基础模型，统一解决指令理解与全身平衡控制的耦合难题
工程与产业观察
该工作验证了“大模型推理+结构化动作原语”在人形机器人零样本任务中的有效性，为解决具身智能中语义到物理执行的鸿沟提供了新范式。其CoA机制降低了端到端策略对海量数据的依赖，对加速人形机器人在非结构化家庭场景的落地具有重要工程参考价值。
英文摘要 (Abstract)
Humanoid loco-manipulation, which integrates whole-body locomotion with dexterous manipulation, remains a fundamental challenge in robotics. Beyond whole-body coordination and balance, a central difficulty lies in understanding human instructions and translating them into coherent sequences of embodied actions. Recent advances in foundation models provide transferable multimodal representations and reasoning capabilities, yet existing efforts remain largely restricted to either locomotion or manipulation in isolation, with limited applicability to humanoid settings. In this paper, we propose Humanoid-COA, the first humanoid agent framework that integrates foundation model reasoning with an Embodied Chain-of-Action (CoA) mechanism for zero-shot loco-manipulation. Within the perception--reasoning--action paradigm, our key contribution lies in the reasoning stage, where the proposed CoA mechanism decomposes high-level human instructions into structured sequences of locomotion and manipulation primitives through affordance analysis, spatial inference, and whole-body action reasoning. Extensive experiments on two humanoid robots, Unitree H1-2 and G1, in both an open test area and an apartment environment, demonstrate that our framework substantially outperforms prior baselines across manipulation, locomotion, and loco-manipulation tasks, achieving robust generalization to long-horizon and unstructured scenarios. Project page: https://humanoid-coa.github.io/
作者：Congcong Wen, Geeta Chandra Raju Bethala, Yu Hao, Niraj Pudasaini, Hao Huang, Shuaihang Yuan, Baoru Huang, Anh Nguyen, Mengyu Wang, Anthony Tzes, Yi Fang
来源
本页事实对应的公开页面，以原文为准。