One Residual with Three Reuses: A Wristband Front End for Gesture Sensing
2026-08-17 • Machine Learning
Machine LearningHardware ArchitectureHuman-Computer Interaction
AI summaryⓘ
The authors studied a small, low-power wristband system that uses both a tiny motion sensor (IMU) and a radar sensor to continuously detect hand gestures and monitor movements. Their design cleverly shares certain calculations to save memory and energy, allowing the device to wake up only when needed and improve tracking accuracy. Tested on several public datasets, their system showed good detection rates while using less energy and reducing error compared to standard methods. The work focuses on the design approach, with actual hardware measurements planned for future work.
MEMS IMUFMCW radargesture recognitionKalman filterclassifier gatingresidual generatorenergy efficiencypose trackingmicrocontroller unitsensor fusion
Authors
Sam Rifaki
Abstract
Continuous wrist-worn hand sensing for gesture interfaces and motor symptom monitoring needs an always-on front end that fits inside a coin-cell power budget while pairing a micro-electro-mechanical-systems (MEMS) inertial measurement unit (IMU) with a 60 GHz frequency-modulated continuous-wave (FMCW) radar to stay robust under occlusion and on-body drift. We present a design study of such a wristband front end in which classifier wake-up gating, mmWave versus IMU routing, and innovation-based EKF measurement reweighting share a single on-chip residual generator. The shared generator occupies 14.4 KB of program memory and 278 B of state and runs at 110K multiply-accumulates (MACs) per frame on an Ambiq Apollo4 Blue Plus class edge microcontroller unit (MCU). Across four public sensor data corpora (IPN Hand, SHREC 2021, MiliPoint 60 GHz FMCW radar, EAT-Radar) the front end reaches detection probability $P_D = 0.72/0.80$ at a 1% false-alarm rate, sustains a 47% classifier invocation energy reduction at 90% gesture detection recall, and lowers pose tracking root-mean-square error by $4.6\times$ under measurement bias drift relative to an adaptive Kalman with $R$-inflation baseline. Measured silicon power and on-body capture are deferred to follow-on hardware; the contribution here is a design study.