SlipSense: Multimodal Tactile Learning for Low-Latency and Generalized Slip Detection
SlipSense fuses a 32x32 piezoresistive array and MEMS accelerometer to detect robotic grip slips within 23.1 ms, generalizing zero-shot across platforms.
SlipSense is a multimodal tactile slip-detection framework built on TacV5, a sensor combining a 32x32 piezoresistive array at 240 Hz and a 3-axis MEMS accelerometer at 8 kHz. It performs modality-specific encoding, intra-sensor fusion, and cross-modal attention with causal temporal prediction at 240 Hz. On a 1.4-million-frame dataset spanning 37 objects it achieves 96.7% Macro F1 with a false-positive rate below 1.6%, detecting 76% of slip events within 23.1 ms. Trained solely on UMI data, it transfers zero-shot to a Tesollo dexterous hand across unseen objects, sensor units, and platforms.
- TacV5 sensor pairs 32x32 piezoresistive array (240 Hz) with 3-axis MEMS accelerometer (8 kHz)
- 96.7% Macro F1, false-positive rate under 1.6%, 76% of slips detected within 23.1 ms
- Evaluated on 1.4 million frames across 37 objects
- Zero-shot transfer from UMI data to Tesollo dexterous hand without retraining
From the original article
1 min read at arxiv.orgSlip 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.
By Tong Jian · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.