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

Forum topic · 小凯 · 2026-09-16

Summary

SlipSense is a multimodal tactile slip-detection framework built on TacV5, a compact sensor combining a 32×32 piezoresistive array running at 240 Hz with a 3-axis MEMS accelerometer sampling at 8 kHz. The piezoresistive array captures spatial pressure distributions while the accelerometer captures friction-induced vibrations, providing complementary slip cues. The framework uses modality-specific encoding, intra-sensor fusion, and cross-modal attention to make causal temporal predictions at 240 Hz. Trained and evaluated on a dataset of 1.4 million frames spanning 37 objects, SlipSense achieves 96.7% macro F1 with a false positive rate below 1.6%, detecting 76% of slip events within 23.1 ms. Notably, when trained only on UMI data, the model zero-shot generalizes to a Tesollo dexterous hand and transfers to unseen objects, different sensor units, and different robot platforms without retraining. Paper: arXiv 2609.15910.

Overview

Slip detection is fundamental to dexterous manipulation, yet existing systems often lack precise characterization of detection latency and cross-platform generalization. SlipSense addresses this with a multimodal tactile slip-detection framework built on TacV5, a compact sensor that integrates:

A 32×32 piezoresistive array operating at 240 Hz, capturing spatial pressure distributions
A 3-axis MEMS accelerometer operating at 8 kHz, capturing friction-induced vibrations

These modalities provide complementary slip cues. The framework performs modality-specific encoding, intra-sensor fusion, and cross-modal attention with causal temporal prediction at 240 Hz.

Key Results

Evaluated on a dataset of 1.4 million frames spanning 37 objects, demonstrating the complementarity of the two sensing modalities
96.7% macro F1 with a false positive rate below 1.6%
Detects 76% of slip events within 23.1 ms
When trained only on UMI data, SlipSense zero-shot generalizes to a Tesollo dexterous hand
Transfers to unseen objects, different sensor units, and different robot platforms without retraining

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

Summary

Overview

Key Results

Links

Tags