# GraspTune：用于鲁棒抓取的触觉驱动执行细化

> 原文链接：https://robotics.hellobike.com/papers/2026-09-21-2609-24180
> 频道：papers | 更新日期：2026-09-21 | 标签：arxiv, cs.RO
> 核心摘要：GraspTune用触觉驱动的有界残差TCP运动细化视觉抓取提案，并在仿真和UR5e真机上验证稳抓提升。

# GraspTune：用于鲁棒抓取的触觉驱动执行细化

::: v-pre
> 原文链接：[GraspTune: Tactile-Driven Execution Refinement for Robust Grasping](https://arxiv.org/abs/2609.24180)（arXiv 2609.24180 · 发布日期：2026-09-21）

**GraspTune: Tactile-Driven Execution Refinement for Robust Grasping**

GraspTune用触觉驱动的有界残差TCP运动细化视觉抓取提案，并在仿真和UR5e真机上验证稳抓提升。

## 核心要点

- 视觉抓取提案虽进展迅速，但执行阶段转化为稳定物理抓取仍具挑战。
- 方法结合局部深度、触觉、状态和历史学习接触语义，并用PPO对齐闭环执行。
- 仿真中在20类物体、6万余次执行上，四种提案器的稳定抓取成功率均提升。
- 真机1000余次试验中，GraspNet执行成功率由71.0%升至84.3%。

**验证范围与局限**：验证范围包括20类物体的6万余次仿真执行，以及UR5e与Xense指尖传感器上的1000余次真机试验。

## 英文摘要 (Abstract)

Visual grasp proposal generation has advanced rapidly, yet converting a selected proposal into a stable physical grasp remains a central execution-stage challenge. This paper introduces GraspTune, a tactile-driven execution-stage refinement framework that starts from a nominal proposal and applies bounded residual TCP motions during approach, contact formation, and final grasp execution. GraspTune learns control-facing contact semantics from local depth, tactile signals, state, and history using state-conditioned expert contact queries and multi-task supervision for contact change, contact risk, and post-close readiness. The representation conditions a diffusion-pretrained residual policy and is aligned with PPO for closed-loop execution. Across more than 60,000 simulated executions over 20 object categories, GraspTune establishes an execution-layer benefit across four proposal generators, raising stable grasp success by +19.22, +9.55, +12.45, and +20.70 percentage points for GraspNet, Contact-GraspNet, AnyGrasp, and VGN. A four-fold held-out category study raises unseen-object execution from 54.58% to 70.33%, showing category-disjoint generalization of contact correction. Across more than 1,000 real-robot trials on a UR5e setup with Xense fingertip sensors, GraspTune raises GraspNet execution from 71.0% to 84.3%, validating direct transfer without realworld policy fine-tuning. Together, these results turn visually plausible proposals into stable physical grasps for downstream contact-rich manipulation. A supplementary video is available at https://youtu.be/kcq7fSLNtzU.

作者：Juntao Li, Xingke Xia, Sichao Liu, Daqiang Guo
:::

## 原始参考来源 (Sources)

- [arXiv 2609.24180：GraspTune: Tactile-Driven Execution Refinement for Robust Grasping](https://arxiv.org/abs/2609.24180)