# TACIT：用于灵巧操作中空间注意力的触觉接触监督

> 原文链接：https://robotics.hellobike.com/papers/2026-09-21-2609-24507
> 频道：papers | 更新日期：2026-09-21 | 标签：arxiv, cs.RO
> 核心摘要：TACIT利用遥操作示教中的触觉接触监督空间注意力，并在真实机器人球放置和插销插入等基准上验证少样本操作表现。

# TACIT：用于灵巧操作中空间注意力的触觉接触监督

::: v-pre
> 原文链接：[TACIT: Tactile Contact Supervision for Spatial Attention in Dexterous Manipulation](https://arxiv.org/abs/2609.24507)（arXiv 2609.24507 · 发布日期：2026-09-21）

**TACIT: Tactile Contact Supervision for Spatial Attention in Dexterous Manipulation**

TACIT利用遥操作示教中的触觉接触监督空间注意力，并在真实机器人球放置和插销插入等基准上验证少样本操作表现。

## 核心要点

- 少量示教训练的视觉运动策略可能复现轨迹，却难以跟随物体位置变化。
- TACIT用触觉接触在相机点云上生成高斯目标，监督注意力并条件化视触觉扩散策略。
- 真实基准中，TACIT在球放置和插销插入达66.7%与73.3%成功率，高于对照。
- 跨三个训练种子，TACIT优于输入匹配融合和无显式注意力监督的结构匹配对照。

**验证范围与局限**：验证限于评估工作空间内，主要包括真实机器人球放置和插销插入，以及真实球与仿真插销的种子实验。

## 英文摘要 (Abstract)

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.

作者：Yanhou Lai, Fucai Zhu, Ruiqiang Wang, Koichi Hashimoto
:::

## 原始参考来源 (Sources)

- [arXiv 2609.24507：TACIT: Tactile Contact Supervision for Spatial Attention in Dexterous Manipulation](https://arxiv.org/abs/2609.24507)