GelNeuro: A Sensing-Computing Integrated Neuromorphic Tactile System for Texture Recognition
2026-07-06 • Robotics
Robotics
AI summaryⓘ
The authors developed GelNeuro, a system that directly connects a touch sensor with a small, efficient neuromorphic chip to quickly recognize textures by feel. Unlike previous setups that needed a computer in between, their design processes the sensor's signals right on the chip using special neural networks. They improved accuracy with a method that adjusts how the chip handles data. Tested on 15 different textures, their system identified them with over 96% accuracy while using very little power compared to usual computers. This shows their approach can do smart touch sensing efficiently on small devices.
neuromorphic sensingvisuo-tactile systemGelSight Minidynamic vision sensor (DVS)spiking convolutional neural network (SCNN)weight clampingtexture recognitionenergy-efficient computinghardware-in-the-loopneuromorphic system-on-chip
Authors
Luoyang Bian, Xinpan Meng, Zhenghua Ma, Houcheng Li, Long Cheng
Abstract
Neuromorphic visuo-tactile sensing offers a promising paradigm for low-latency and low-power robotic perception. However, existing systems still rely heavily on a host computer for event readout, preprocessing, or relaying prior to chip inference. This paper presents GelNeuro, a fully integrated sensing-computing visuo-tactile system that directly pairs a GelSight Mini-based optical tactile front end with the Speck2f neuromorphic system-on-chip (SoC). Contact-induced marker motions are captured as dynamic vision sensor (DVS) events and routed through the on-chip network to a spiking convolutional neural network (SCNN) classifier. To mitigate accuracy degradation during 8-bit deployment, a hardware-aware weight clamping strategy is introduced. Evaluated on a 15-class natural texture recognition task, hardware-in-the-loop testing on the physical chip achieves a 96.3% accuracy within an 80 ms inference window. Notably, the system consumes only 19.6 mW of board-level active power-over three orders of magnitude lower than conventional CPU/GPU baselines on the same benchmark. GelNeuro also exhibits robust generalization across unseen contact depths, demonstrating the viability of direct sensor-to-chip tactile recognition on edge neuromorphic hardware.