SlipSense: Multimodal Tactile Learning for Low-Latency and Generalized Slip Detection

2026-09-14

AI Summary

为解决现有滑移检测系统精度不足和泛化能力差的问题，SlipSense利用多模态触觉学习框架结合压力分布和振动信息实现低延迟高精度的滑移检测。

Abstract

Slip detection is fundamental to dexterous manipulation, yet existing systems often lack precise characterization of detection latency and cross-platform generalization. We present SlipSense, a multimodal tactile slip-detection framework built on TacV5, a compact sensor integrating a $32 \times 32$ piezoresistive array operating at 240 Hz and a 3-axis MEMS accelerometer operating at 8 kHz. The piezoresistive array captures spatial pressure distributions, while the accelerometer captures friction-induced vibrations, providing complementary slip cues. The framework performs modality-specific encoding, intra-sensor fusion, and cross-modal attention with causal temporal prediction at 240 Hz. Experiments on a dataset of 1.4 million frames spanning 37 objects demonstrate the complementarity of the two modalities. SlipSense achieves 96.7% Macro F1 with a false-positive rate below 1.6%, detecting 76% of slip events within 23.1 ms. When trained solely on UMI data, SlipSense generalizes zero-shot to a Tesollo dexterous hand, transferring across unseen objects, distinct sensor units, and robotic platforms without retraining.

Problem

• slip detection
• detection latency
• cross-platform generalization

Innovation

• multimodal tactile learning
• low-latency slip detection
• cross-platform generalization
• intra-sensor fusion
• cross-modal attention