---
title: "PanoTac: A Dense Three-Axis Tactile Sensor for Robust Touch-Centric Manipulation"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.03520v1"
permalink: "https://feed.astralor.com/items/itm_e8d53043cac8636aa0394a70"
published: "2026-11-02T17:55:07.000Z"
score: 58
channel: "tech"
tags: ["RAG","多模态","PanoTac","Dense Three-Axis Tactile","Sensor","Robust Touch-Centric Manipulation","Contact-rich","When"]
---

# PanoTac: A Dense Three-Axis Tactile Sensor for Robust Touch-Centric Manipulation

## 速览

Contact-rich manipulation benefits from tactile feedback that captures both detailed contact geometry and interaction forces. When scooping grains, contact patterns help infer spoon orientation, while resistance transmi…

## 关键点

- Contact-rich manipulation benefits from tactile feedback that captures both detailed contact geometry and interaction forces.
- When scooping grains, contact patterns help infer spoon orientation, while resistance transmitted through the grasp guides motion.
- To provide these complementary sensing capabilities, we present PanoTac, a low-cost, compliant tactile fingertip designed for dense three-axis tactile sensing.

## 全文

Contact-rich manipulation benefits from tactile feedback that captures both detailed contact geometry and interaction forces. When scooping grains, contact patterns help infer spoon orientation, while resistance transmitted through the grasp guides motion. To provide these complementary sensing capabilities, we present PanoTac, a low-cost, compliant tactile fingertip designed for dense three-axis tactile sensing. Each fingertip provides a $12 \times 32 \times 3$ tactile representation, with one normal ($z$) and two shear ($x$, $y$) response components at each taxel. The sensor operates at 60 Hz and costs less than $50 per fingertip. Sensor characterization quantifies response repeatability and consistency across sensor instances and contact locations. We integrate PanoTac into a robotic system with a visuo-tactile pipeline. Across test-tube preparation, grain scooping, and salt pouring, the resulting policies outperform vision-only baselines by an average of 46.7 percentage points. Ablations show that removing either spatial contact information or shear feedback reduces overall performance across the task suite. Our project page is available at https://panotac.github.io.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_e8d53043cac8636aa0394a70