提出一种实时低抖动手部动作重定向算法，提升机器人操作数据质量。
Smooth Operator: A Real-Time Sampling-Based Algorithm for Kinematic Hand Retargeting
- 基于采样控制思想，无需梯度优化，避免局部最优
- 真实用户实验中任务成功率54.1%，疲劳感最低
- 适合高精度灵巧操作与人机协同研究
学习型机器人操作（如视觉-语言-动作模型和视频动作模型）高度依赖高质量遥操作数据，其性能上限由人类示范质量决定。现有基于梯度的重定向算法常陷入不同局部极小值，导致抖动，影响数据质量和操作体验。为此，本文提出采样式重定向器（SBR），一种源自采样控制理论的无梯度方法，专为低抖动、实时运动学重定向设计。我们在仿真和一项包含18名参与者、执行3个复杂操作任务的真实世界用户研究中评估SBR。相比基于梯度的基线方法，SBR实现了最高的总体任务成功率（54.1%），同时显著降低操作者认知疲劳，获得最低的NASA-TLX工作负荷评分（36.4/100）。最终，SBR被证实是一种高效且直观的灵巧操作重定向方案，并为未来重定向研究提供了严谨的基准评测方法。
原文摘要 · Abstract (English)
Advances in learning-based robotic manipulation, such as Vision-Language-Action (VLA) models and Video Action Models (VAMs), heavily rely on high-quality teleoperation data. Their capabilities are strictly upper-bounded by the quality of the underlying human demonstrations. Current gradient-based retargeting algorithms often converge to different local minima, resulting in jitter that affects data quality and teleoperation experience. To address this, we introduce the Sampling-Based Retargeter (SBR), a novel gradient-free retargeting method drawn from the rich literature of sampling-based control and explicitly designed for low-jitter, real-time kinematic retargeting. We evaluate SBR both in simulation and through a rigorous real-world user study involving 18 participants performing 3 complex manipulation tasks. Compared to gradient-based baselines, SBR achieved the highest overall task success rate (54.1%) while significantly reducing operator cognitive fatigue, recording the lowest NASA-TLX workload score (36.4 out of 100). Ultimately, we establish SBR as a highly effective, intuitive retargeter for dexterous manipulation, providing the community with a rigorous benchmarking methodology to guide future retargeting research.
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。