Abstract
Ubiquitous positioning for pedestrians in adverse environments has been a long standing challenge. Despite dramatic progress made by Deep Learning, multi-sensor deep odometry systems still 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 select and compare three sensor modalities, i.e., an Inertial Measurement Unit (IMU), a millimetre-wave (mmWave) radar, and a thermal infrared camera, and implement their deep odometry inference engines to run in real-time. A pipeline for deploying deep odometry on edge platforms with different resource constraints is proposed. We design a LoRa link for positional data backhaul and project aggregated positions of deep odometry into the global frame. We find that a simple EKF backend is sufficient for generic odometry 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.
Original language | English |
---|---|
Title of host publication | Proceedings - The 1st Workshop on Cyber Physical Systems for Emergency Response, CPS-ER 2022 |
Editors | Niki Trigoni, Jack Stankovic, Andrew Markham |
Place of Publication | Piscataway NJ USA |
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Pages | 1-6 |
Number of pages | 6 |
ISBN (Electronic) | 9781665470360 |
ISBN (Print) | 9781665470377 |
DOIs | |
Publication status | Published - 2022 |
Event | Workshop on Cyber Physical Systems for Emergency Response 2022 - Online, Italy Duration: 3 May 2022 → 3 May 2022 Conference number: 1st https://ieeexplore.ieee.org/xpl/conhome/9804977/proceeding (Proceedings) |
Conference
Conference | Workshop on Cyber Physical Systems for Emergency Response 2022 |
---|---|
Abbreviated title | CPS-ER 2022 |
Country/Territory | Italy |
Period | 3/05/22 → 3/05/22 |
Internet address |
Keywords
- Deep Learning, edge computing, ubiquitous positioning