# TacPAC：面向接触丰富操作的 World-Action Models 中的触觉预测与实时动作校正

> 原文链接：https://robotics.hellobike.com/papers/2026-09-04-2609-05266
> 频道：papers | 更新日期：2026-09-04 | 标签：arxiv, cs.RO
> 核心摘要：TacPAC将触觉预测转为实时动作校正，在五个真机接触丰富操作任务上提升视觉基模型表现。

# TacPAC：面向接触丰富操作的 World-Action Models 中的触觉预测与实时动作校正

::: v-pre
> 原文链接：[TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulation](https://arxiv.org/abs/2609.05266)（arXiv 2609.05266 · 发布日期：2026-09-04）

**TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulation**

TacPAC将触觉预测转为实时动作校正，在五个真机接触丰富操作任务上提升视觉基模型表现。

## 核心要点

- 视觉中心的预测会遗漏局部接触线索，直接预测未来触觉仅恢复三分之一可达增益。
- TacPAC缓存计划所依赖的预测接触和表征，用新触觉图像校正尚未执行的动作。
- 单次校正只需遍历缓存，比重新生成动作块便宜20.7倍。
- 五个真机任务中 TacPAC 均领先，平均表现由22%提升至64%，代码已提供。

**验证范围与局限**：验证限于五个真机任务，涵盖精密插入、易碎物体处理、物体重定向和长时程操作。

## 英文摘要 (Abstract)

World-action models guide action generation with predicted future observations, but vision-centric predictions miss the local contact cues that decide contact-rich manipulation. However, naively predicting future tactile observations as additional views recovers only a third of the achievable gain in our experiments. This gap reflects a timing mismatch: predictions precede execution, while tactile feedback arrives during it. We introduce TacPAC, which turns tactile prediction into real-time action correction. Once the base model has planned an action chunk, TacPAC caches the predicted contact that plan was conditioned on together with the plan's own representation, and a tactile expert reads each newly observed tactile image against that cache to correct the actions not yet executed. Feedback is thus interpreted against what the plan anticipated rather than in isolation, and one correction is a single pass over that cache, $20.7\times$ cheaper than regenerating the chunk. On five real-robot tasks spanning precision insertion, fragile-object handling, object reorientation, and long-horizon manipulation, TacPAC leads every task and raises the average from 22% for its vision-only base model to 64%. Code is available at https://github.com/LogosRoboticsGroup/TacPAC.

作者：麻滋沛, Wei, Xiaofei, Junzhe Jiang, Shunlin Lu, Li Zhang
:::

## 原始参考来源 (Sources)

- [arXiv 2609.05266：TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulation](https://arxiv.org/abs/2609.05266)