Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

An Event-Driven E-Skin System with Dynamic Binary Scanning and real time SNN Classification

Gaishan Li, Zhengnan Fu, Anubhab Tripathi, Junyi Yang, Arindam Basu

TL;DR

This work demonstrates a fully integrated, event-driven pipeline from analog sensing to neuromorphic classification, offering an efficient solution for robotic perception and human-computer interaction.

Abstract

This paper presents a novel hardware system for high-speed, event-sparse sampling-based electronic skin (e-skin)that integrates sensing and neuromorphic computing. The system is built around a 16x16 piezoresistive tactile array with front end and introduces a event-based binary scan search strategy to classify the digits. This event-driven strategy achieves a 12.8x reduction in scan counts, a 38.2x data compression rate and a 28.4x equivalent dynamic range, a 99% data sparsity, drastically reducing the data acquisition overhead. The resulting sparse data stream is processed by a multi-layer convolutional spiking neural network (Conv-SNN) implemented on an FPGA, which requires only 65% of the computation and 15.6% of the weight storage relative to a CNN. Despite these significant efficiency gains, the system maintains a high classification accuracy of 92.11% for real-time handwritten digit recognition. Furthermore, a real neuromorphic tactile dataset using Address Event Representation (AER) is constructed. This work demonstrates a fully integrated, event-driven pipeline from analog sensing to neuromorphic classification, offering an efficient solution for robotic perception and human-computer interaction.

An Event-Driven E-Skin System with Dynamic Binary Scanning and real time SNN Classification

TL;DR

This work demonstrates a fully integrated, event-driven pipeline from analog sensing to neuromorphic classification, offering an efficient solution for robotic perception and human-computer interaction.

Abstract

This paper presents a novel hardware system for high-speed, event-sparse sampling-based electronic skin (e-skin)that integrates sensing and neuromorphic computing. The system is built around a 16x16 piezoresistive tactile array with front end and introduces a event-based binary scan search strategy to classify the digits. This event-driven strategy achieves a 12.8x reduction in scan counts, a 38.2x data compression rate and a 28.4x equivalent dynamic range, a 99% data sparsity, drastically reducing the data acquisition overhead. The resulting sparse data stream is processed by a multi-layer convolutional spiking neural network (Conv-SNN) implemented on an FPGA, which requires only 65% of the computation and 15.6% of the weight storage relative to a CNN. Despite these significant efficiency gains, the system maintains a high classification accuracy of 92.11% for real-time handwritten digit recognition. Furthermore, a real neuromorphic tactile dataset using Address Event Representation (AER) is constructed. This work demonstrates a fully integrated, event-driven pipeline from analog sensing to neuromorphic classification, offering an efficient solution for robotic perception and human-computer interaction.
Paper Structure (9 sections, 5 figures, 1 table)

This paper contains 9 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Sensor, front-end and scanning algorithm
  3. Sensor and front-end hardware system
  4. Event-based Binary Scan Search Strategy
  5. Dataset collection
  6. Result and iscussion
  7. Data compression results
  8. Recognition of Handwritten Digits
  9. Conclusion

Figures (5)

  • Figure 1: (a) Proposed overall neuromorphic hardware system, (b) Data heatmap, (c) Event-based Binary Scan Search Strategy (Pulse display of the 16 strongest channels), (d) Convolutional spiking neural network structure used in this system
  • Figure 2: Schematic of the readout hardware system of tactile sensors
  • Figure 3: Comparison of traditional and proposed Scanning Strategies
  • Figure 4: (a) Accumulated pressure map of digit "5", (b) Raster plot of spikes, (c) Firing rate histogram, (d) Efficiency in compression, storage and data sparsity
  • Figure 5: Trade-off between Compression Ratio (compared with raw data) and Classification Accuracy under Different Delta Values