用人体操作数据生成并优化机器人动作，让精细操作更可靠。
DexSynRefine: Synthesizing and Refining Human-Object Interaction Motion for Physically Feasible Dexterous Robot Actions
- 将人体操作数据作为运动先验，分两步合成并修正手物轨迹。
- 在五个任务中，实测成功率比传统方法提升50-70个百分点。
- 适合做精细抓取、需物理合理性验证的机器人控制研究者。
从人体-物体交互（HOI）数据学习精细操作可替代机器人遥操作，但现有演示通常稀疏且仅含运动学信息，直接迁移易受本体差异和接触动力学影响。我们提出DexSynRefine，将HOI数据视为结构化运动先验而非可执行动作。首先，基于HOI运动流形流原语（HOI-MMFP）生成依赖任务与初始物体状态的手物轨迹；随后通过任务空间残差强化学习实现物理对齐，并利用本体感知历史推断缺失的接触动力学上下文。在五项精细操作任务中，各阶段解决不同瓶颈：HOI-MMFP提升轨迹一致性与平滑性，任务空间残差提供最强物理对齐表征，接触动力学自适应实现鲁棒真实执行。整体相较运动学重定向，真实场景成功率提升50-70个百分点。
原文摘要 · Abstract (English)
Learning dexterous manipulation from human-object interaction (HOI) data offers a scalable alternative to robot teleoperation, but HOI demonstrations are typically sparse and purely kinematic, making direct retargeting unreliable under embodiment mismatch and contact-rich dynamics. We present DexSynRefine, a coupled framework that treats HOI data as structured motion priors rather than executable robot actions. DexSynRefine first synthesizes hand-object trajectories conditioned on the task and initial object state using HOI Motion Manifold Flow Primitives (HOI-MMFP), a motion prior for coupled hand-object motion. It then physically grounds them with task-space residual reinforcement learning and adapts execution by inferring missing contact-dynamics context from proprioceptive history. Across five dexterous manipulation tasks, each stage addresses a complementary bottleneck: HOI-MMFP improves trajectory consistency and smoothness, task-space residuals provide the strongest grounding representation among the tested alternatives, and contact-dynamics adaptation enables robust real-world execution. Together, DexSynRefine improves real-world success rates over kinematic retargeting by 50-70~percentage points.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。