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

**Authors:** Binglin, Wang, Xiaole, Jiang, Zicheng Teng, Xinqi Liu, Yunzhu Li, Lerrel Pinto, Zichen Jeff Cui, Binghao Huang  
**Published:** 2 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.03520) · [PDF](https://arxiv.org/pdf/2611.03520) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.03520.html)

## Key numbers

- **12×**: Each fingertip provides a 12 × 32 × 3 tactile representation
- **46.7**: the resulting policies outperform vision-only baselines by an average of 46.7 percentage points

## Abstract

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 × 32 × 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.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.