SUBTA让机器人更懂用户意图，协作装配更准更省力
SUBTA: A Framework for Supported User-Guided Bimanual Teleoperation in Structured Assembly
- 通过意图识别+任务图规划，动态提供双手操作支持
- 用户实验显示定位与姿态误差降低，心理负担减少34%
- 适合需要高精度协同装配的工业远程操作场景
在人机协作中，共享自主权可提升人类表现。有效的机器人辅助需精准推断人类意图并理解任务结构，以确定最佳支持时机与方式。本文提出SUBTA系统，用于结构化装配中的双臂遥操作，融合学习到的意图估计、场景图任务规划和上下文依赖运动辅助。通过12名用户的对照实验，比较标准遥操作、仅运动支持与SUBTA的表现。线性混合效应分析显示，与标准遥操作相比，SUBTA在位置精度（p<0.001，d=1.18）和姿态精度（p<0.001，d=1.75）上显著更优，同时降低心理负荷（p=0.002，d=1.34）。事后评分表明，SUBTA提供更清晰、可信的视觉反馈和可预测的干预。结果证明，SUBTA显著提升了遥操作的有效性与用户体验。
原文摘要 · Abstract (English)
In human-robot collaboration, shared autonomy enhances human performance through precise, intuitive support. Effective robotic assistance requires accurately inferring human intentions and understanding task structures to determine optimal support timing and methods. In this paper, we present SUBTA, a supported teleoperation system for bimanual assembly that couples learned intention estimation, scene-graph task planning, and context-dependent motion assists. We validate our approach through a user study (N=12) comparing standard teleoperation, motion-support only, and SUBTA. Linear mixed-effects analysis revealed that SUBTA significantly outperformed standard teleoperation in position accuracy (p<0.001, d=1.18) and orientation accuracy (p<0.001, d=1.75), while reducing mental demand (p=0.002, d=1.34). Post-experiment ratings indicate clearer, more trustworthy visual feedback and predictable interventions in SUBTA. The results demonstrate that SUBTA greatly improves both effectiveness and user experience in teleoperation.
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。