# HapticWAM：将想象触觉蒸馏到无需推理时触觉感知的世界-动作模型中

> 原文链接：https://robotics.hellobike.com/papers/2026-09-20-2609-23888
> 频道：papers | 更新日期：2026-09-20 | 标签：arxiv, cs.RO
> 核心摘要：HapticWAM通过异构触觉编码、结构化接触预测与师生蒸馏，解决部署时无指尖触觉的富接触操作，并在真实三项拾放任务验证。

# HapticWAM：将想象触觉蒸馏到无需推理时触觉感知的世界-动作模型中

::: v-pre
> 原文链接：[HapticWAM: Distilling Imagined Touch into a World-Action Model without Inference-Time Tactile Sensing](https://arxiv.org/abs/2609.23888)（arXiv 2609.23888 · 发布日期：2026-09-20）

**HapticWAM: Distilling Imagined Touch into a World-Action Model without Inference-Time Tactile Sensing**

HapticWAM通过异构触觉编码、结构化接触预测与师生蒸馏，解决部署时无指尖触觉的富接触操作，并在真实三项拾放任务验证。

## 核心要点

- 富接触操作中，力、滑移和接触几何在场景图像中可能不明确。
- 方法结合触觉编码、未来接触包预测、Anticipatory Contact Coupling与师生蒸馏。
- 学生模型保留生成式接触头，但移除指尖输入分支以支持无触觉部署。
- 真实三项拾放任务中，学生平均成功率77%，总体82%，一项达95%。

**验证范围与局限**：仅摘要报告在真实设置的三项富接触拾放任务上验证。

## 英文摘要 (Abstract)

Contact-rich manipulation requires estimating forces, slip and contact geometry that can remain ambiguous in scene images. Optical tactile sensors provide both visual observations of the contact surface and mechanical measurements, yet learning from these signals raises two challenges: representing contact beyond appearance and transferring its benefits to a policy that does not require fingertip observations at deployment. We introduce HapticWAM, a world-action model that combines heterogeneous tactile encoding, structured contact prediction and teacher-student distillation. Its teacher encodes gel images together with deformation, shear, distributed forces, resultant wrench and derived contact state into a frozen video backbone. Rather than predicting tactile pixels alone, the model jointly generates actions and a contact package describing future events and mechanics. Anticipatory Contact Coupling uses the previously imagined package to condition attention, preserving a contact-related input when direct tactile observations are unavailable. Haptic-Imagination Distillation transfers both contact futures and action predictions to a student that retains the generative contact head but removes its fingertip input branches. On a real-world setup, across three contact-rich pick-and-place tasks, HapticWAM Student achieves a 77% per-task mean success rate (41 of 50 starts, 82% pooled), reaching 95% on one of the tasks, outperforming the evaluated teacher and baseline configurations.

作者：Mikhail Sannikov, Ilya Mikhalchuk, Konstantin N. Gubernatorov, Petr Kovalev, Ogunwoye Faith Oluwatobi, Dzmitry Tsetserukou
:::

## 原始参考来源 (Sources)

- [arXiv 2609.23888：HapticWAM: Distilling Imagined Touch into a World-Action Model without Inference-Time Tactile Sensing](https://arxiv.org/abs/2609.23888)