外观
论文arXiv 2512.2507210 个月前
Choice Policy策略实现人形机器人全身协调操作与高效数据采集
本文由 AI 根据公开内容整理，可能有误，请以原文为准：Coordinated Humanoid Manipulation with Choice Policies（arXiv 2512.25072）
核心内容
针对人形机器人在非结构化环境中头、手、腿全身协调控制难题，研究团队发布了一套结合模块化遥操作接口与可扩展学习框架的系统。该系统通过Choice Policy模仿学习方法生成多候选动作并评分，解决了多模态行为建模与快速推理的平衡问题。实机验证涵盖洗碗机装载与全身移动操作擦白板两项任务，结果表明该方法在成功率上显著优于Diffusion Policy及标准Behavior Cloning基线。
技术架构将人形控制解耦为手眼协调、抓取原语、臂端跟踪与运动控制四个直观子模块，大幅提升了高质量示教数据的采集效率。Choice Policy通过生成多个候选动作并学习评分机制，有效应对复杂操作中的多模态分布。实验证实手眼协调能力是长程任务成功的决定性因素，该工作为人形机器人在开放环境下的规模化数据收集与协调操作学习提供了可复现的工程路径。
关键看点
- Choice Policy架构：采用生成多候选动作并学习评分的模仿学习机制，兼顾快速推理与多模态行为建模，性能优于扩散策略
- 模块化遥操作：将控制解耦为手眼协调、抓取原语、臂端跟踪及运动子模块，显著提升人形机器人高质量示教数据采集效率
- 长程任务验证：在洗碗机装载与白板擦拭实机测试中，证实手眼协同能力是决定长程操作成功率的关键要素
- 基线对比优势：在非结构化环境操作任务中，该框架的鲁棒性与任务完成率显著超越标准行为克隆与Diffusion Policy
工程与产业观察
该研究通过控制解耦降低人形机器人数据采集门槛，并以Choice Policy替代高算力消耗的扩散模型，为具身智能提供了兼顾训练效率与推理实时性的新范式。其强调的手眼协同与模块化遥操方案，对解决当前人形机器人长程操作数据匮乏与泛化难问题具有直接工程参考价值。
英文摘要 (Abstract)
Humanoid robots hold great promise for operating in human-centric environments, yet achieving robust whole-body coordination across the head, hands, and legs remains a major challenge. We present a system that combines a modular teleoperation interface with a scalable learning framework to address this problem. Our teleoperation design decomposes humanoid control into intuitive submodules, which include hand-eye coordination, grasp primitives, arm end-effector tracking, and locomotion. This modularity allows us to collect high-quality demonstrations efficiently. Building on this, we introduce Choice Policy, an imitation learning approach that generates multiple candidate actions and learns to score them. This architecture enables both fast inference and effective modeling of multimodal behaviors. We validate our approach on two real-world tasks: dishwasher loading and whole-body loco-manipulation for whiteboard wiping. Experiments show that Choice Policy significantly outperforms diffusion policies and standard behavior cloning. Furthermore, our results indicate that hand-eye coordination is critical for success in long-horizon tasks. Our work demonstrates a practical path toward scalable data collection and learning for coordinated humanoid manipulation in unstructured environments.
作者：Haozhi Qi, Yen-Jen Wang, Toru Lin, Brent Yi, Yi Ma, Koushil Sreenath, Jitendra Malik
来源
本页事实对应的公开页面，以原文为准。