Edge Training and Inference with Analog ReRAM Technology for Hand Gesture Recognition

TL;DR

This paper explores the use of analog ReRAM technology for low-power, real-time hand gesture recognition at the edge, demonstrating high accuracy and hardware-aware simulation for practical HMI applications.

Contribution

It introduces a hardware-aware simulation framework for analog ReRAM-based in-memory computing tailored for edge gesture recognition, avoiding large crossbar arrays and validating with experimental data.

Findings

Achieved approximately 91.4% classification accuracy.

Demonstrated hardware-aware simulation incorporating device non-idealities.

Validated potential for real-time, low-power HMI systems at the edge.

Abstract

Tactile hand gesture recognition is a crucial task for user control in the automotive sector, where Human-Machine Interactions (HMI) demand low latency and high energy efficiency. This study addresses the challenges of power-constrained edge training and inference by utilizing analog Resistive Random Access Memory (ReRAM) technology in conjunction with a real tactile hand gesture dataset. By optimizing the input space through a feature engineering strategy, we avoid relying on large-scale crossbar arrays, making the system more suitable for edge deployment. Through realistic hardware-aware simulations that account for device non-idealities derived from experimental data, we demonstrate the functionalities of our analog ReRAM-based analog in-memory computing for on-chip training, utilizing the state-of-the-art Tiki-Taka algorithm. Furthermore, we validate the classification accuracy of approximately 91.4% for post-deployment inference of hand gestures. The results highlight the potential of analog ReRAM technology and crossbar architecture with fully parallelized matrix computations for real-time HMI systems at the Edge.