# exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation

arXiv: https://arxiv.org/abs/2509.14688 · HTML: https://mlsanity.com/paper/2509.14688/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2025.

## Built on by (most cited first, 14 of 14)

- [World Action Models: The Next Frontier in Embodied AI](https://mlsanity.com/paper/2605.12090/) (2026)
- [Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols](https://mlsanity.com/paper/2512.02787/) (2025)
- [Data Pyramid for Embodied Manipulation: A Survey](https://mlsanity.com/paper/2607.24744/) (2026)
- [AoE: Always-on Egocentric Human Video Collection for Embodied AI](https://mlsanity.com/paper/2602.23893/) (2026)
- [HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing](https://mlsanity.com/paper/2608.12122/) (2026)
- [UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception](https://mlsanity.com/paper/2604.14089/) (2026)
- [YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale](https://mlsanity.com/paper/2606.10244/) (2026)
- [Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation](https://mlsanity.com/paper/2606.29941/) (2026)
- [Tac-DINO: Learning Vision-Tactile Features with Patch Alignment](https://mlsanity.com/paper/2606.12069/) (2026)
- [RAPID: Reconfigurable, Adaptive Platform for Iterative Design](https://mlsanity.com/paper/2602.06653/) (2026)
- [The Potential of Haptic Foundation Models](https://mlsanity.com/paper/2608.28664/) (2026)
- [N0-Foundation: Towards the Age of Tactile Intelligence](https://mlsanity.com/paper/2608.29601/) (2026)
- [BiView-Touch: Learning Bimanual Tactile Representations by Cross-Hand Completion](https://mlsanity.com/paper/2609.23352/) (2026)
- [Self-Supervised Anchoring of Fingertip Sensing to Proprioception and Proactive Actions for Robot Imitation Learning](https://mlsanity.com/paper/2609.29822/) (2026)

## Abstract (arXiv)

Tactile-aware robot learning faces critical challenges in data collection and representation due to data scarcity and sparsity, and the absence of force feedback in existing systems. To address these limitations, we introduce a tactile robot learning system with both hardware and algorithm innovations. We present exUMI, an extensible data collection device that enhances the vanilla UMI with robust proprioception (via AR MoCap and rotary encoder), modular visuo-tactile sensing, and automated calibration, achieving 100% data usability. Building on an efficient collection of over 1 M tactile frames, we propose Tactile Prediction Pretraining (TPP), a representation learning framework through action-aware temporal tactile prediction, capturing contact dynamics and mitigating tactile sparsity. Real-world experiments show that TPP outperforms traditional tactile imitation learning. Our work bridges the gap between human tactile intuition and robot learning through co-designed hardware and algorithms, offering open-source resources to advance contact-rich manipulation research. Project page: https://silicx.github.io/exUMI.