Deep Odometry Systems on Edge with EKF-LoRa Backend for Real-Time Positioning in Adverse Environment
This addresses the problem of cumulative drifting errors in multi-sensor deep odometry for pedestrian positioning, though it is incremental as it builds on existing deep learning and sensor fusion methods.
The paper tackles real-time pedestrian positioning in adverse environments by integrating deep odometry models on edge devices with an EKF-LoRa backend, achieving over 34% accuracy gains compared to standalone systems.
Ubiquitous positioning for pedestrian in adverse environment has served a long standing challenge. Despite dramatic progress made by Deep Learning, multi-sensor deep odometry systems yet pose a high computational cost and suffer from cumulative drifting errors over time. Thanks to the increasing computational power of edge devices, we propose a novel ubiquitous positioning solution by integrating state-of-the-art deep odometry models on edge with an EKF (Extended Kalman Filter)-LoRa backend. We carefully compare and select three sensor modalities, i.e., an Inertial Measurement Unit (IMU), a millimetre-wave (mmWave) radar, and a thermal infrared camera, and realise their deep odometry inference engines which runs in real-time. A pipeline of deploying deep odometry considering accuracy, complexity, and edge platform is proposed. We design a LoRa link for positional data backhaul and projecting aggregated positions of deep odometry into the global frame. We find that a simple EKF based fusion module is sufficient for generic positioning calibration with over 34% accuracy gains against any standalone deep odometry system. Extensive tests in different environments validate the efficiency and efficacy of our proposed positioning system.