发表机构
Tohoku University（东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TACIT利用遥操作演示中的触觉接触监督空间注意力，无需额外标注，在少量演示下显著提升灵巧操作成功率，验证了触觉接触作为空间监督的有效性。
AI 中文摘要
从少量演示中训练的视觉运动策略可能复现演示轨迹，但无法可靠地跟随物体位置的变化。现有的显式注意力方法通常从人工标注或视觉模型中获取空间先验。我们提出TACIT（触觉接触引导注意力），该方法利用遥操作演示中测量的触觉接触来监督空间注意力，无需额外的点标注。先前相机点云上的高斯目标监督一个注意力头，其池化输出条件化一个视觉触觉扩散策略。目标仅在训练期间使用；触觉观测在推理时仍作为输入。在主要的真实机器人基准测试中，每个任务使用十个演示和五个演示放置区域，TACIT在球放置任务上达到66.7%的成功率，在插销插入任务上达到73.3%，而输入匹配的3D视觉触觉融合分别为10.0%和20.0%，仅视觉的DP3分别为20.0%和43.3%。TACIT在每个任务的全部30次试验中均在12秒内进入150毫米手掌到物体接近区域；所有剩余失败均发生在到达之后。在真实球和模拟插销的三种训练种子中，TACIT优于输入匹配的融合和没有显式注意力监督的架构匹配对照，支持监督超越分支容量的贡献。接触前和接触时监督没有一致的排序。这些结果表明，在评估的工作空间内，测量的触觉接触为少量演示中的接近行为提供了有效的空间监督。
英文摘要
Visuomotor policies trained from a few demonstrations may reproduce demonstrated trajectories without reliably following changes in object position. Existing approaches with explicit attention typically obtain spatial priors from human annotation or visual models. We introduce TACIT (tactile contact informs attention), which uses measured tactile contacts from teleoperated demonstrations to supervise spatial attention without additional point annotation. Gaussian targets over preceding camera point clouds supervise an attention head whose pooled output conditions a visuotactile diffusion policy. Targets are used only during training; tactile observations remain inputs at inference. In the primary real-robot benchmark, with ten demonstrations per task and five demonstrated placement regions, TACIT achieves 66.7% success on ball placement and 73.3% on peg insertion, compared with 10.0% and 20.0% for input-matched 3D visuotactile fusion and 20.0% and 43.3% for vision-only DP3. TACIT enters the 150 mm palm-to-object approach region within 12 seconds in all 30 trials per task; all remaining failures occur after arrival. Across three training seeds on real ball and simulated peg, TACIT outperforms input-matched fusion and an architecture-matched control without explicit attention supervision, supporting the contribution of supervision beyond branch capacity. Pre-contact and contact-time supervision show no consistent ordering. These results demonstrate that measured tactile contact provides effective spatial supervision for approach behavior from few demonstrations within the evaluated workspace.
