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

arXiv: https://arxiv.org/abs/2609.15910 · HTML: https://mlsanity.com/paper/2609.15910/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [SSAST: Self-Supervised Audio Spectrogram Transformer](https://mlsanity.com/paper/2110.09784/) (2021)
- [DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation](https://mlsanity.com/paper/2005.14679/) (2020)
- [Sparsh: Self-supervised touch representations for vision-based tactile sensing](https://mlsanity.com/paper/2410.24090/) (2024)
- [Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper](https://mlsanity.com/paper/2507.15062/) (2025)
- [Maintaining Grasps within Slipping Bound by Monitoring Incipient Slip](https://mlsanity.com/paper/1810.13381/) (2018)
- [VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning](https://mlsanity.com/paper/2510.14930/) (2025)
- [Learning to Detect Slip through Tactile Estimation of the Contact Force Field and its Entropy](https://mlsanity.com/paper/2303.00935/) (2023)
- [Multimodal Anomaly Detection based on Deep Auto-Encoder for Object Slip Perception of Mobile Manipulation Robots](https://mlsanity.com/paper/2403.03563/) (2024)
- [A multi-modal tactile fingertip design for robotic hands to enhance dexterous manipulation](https://mlsanity.com/paper/2510.05382/) (2025)
- [Incipient Slip Detection by Vibration Injection into Soft Sensor](https://mlsanity.com/paper/2402.11879/) (2024)
- [Reactive Slip Control in Multifingered Grasping: Hybrid Tactile Sensing and Internal-Force Optimization](https://mlsanity.com/paper/2602.16127/) (2026)
- [A-SLIP: Acoustic Sensing for Continuous In-hand Slip Estimation](https://mlsanity.com/paper/2604.08528/) (2026)

## Abstract (arXiv)

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 × 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.