Electromagnetic Spectrum-Aided Radiation Source Tracking Algorithm
- 6 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 30 (10897798) , 208-212
Abstract
Real-time obstacle avoidance and spectrum sensing in complex environments conflict inherently, making accurate radiation source tracking difficult. This letter establishes an online learning framework by proposing a progressive fusion algorithm combining variational inference and Gaussian processes. An end-to-end neural network that achieves linear-complexity inference with $O(HW + M + nm)$ complexity per time step by mapping depth images and spectrum data into time-optimal trajectories is the main innovation. Through trajectory primitive coordination with REM construction, a dual-update mechanism synchronously optimizes localization and obstacle avoidance. Using Gaussian processes to model positional uncertainty, the variational Bayesian inference engine enables probabilistic source prediction without specialized positioning modules. Simulations show 10-second exploration-localization completion in $30\times 60$ m2 areas and collision-free navigation at 4 m/s in obstacles spaced 0.3-0.6m. Comprehensive high-fidelity simulation studies validate the algorithm’s robustness across diverse environments and radiation source configurations. Compared to traditional optimization-based methods with $O(N^{3})$ complexity and particle filter approaches, our algorithm achieves 15% better localization accuracy, 25% faster convergence, and 40% reduced computational cost while maintaining real-time performance with 15 ms per control cycle. The fusion of model-driven REM and data-driven planning exhibits superior adaptability over conventional spectrum mapping approaches.Keywords
This publication has 10 references indexed in Scilit:
- You Only Plan Once: A Learning-Based One-Stage Planner With Guidance LearningIEEE Robotics and Automation Letters, 2024
- LPNet: A Reaction-Based Local Planner for Autonomous Collision Avoidance Using Imitation LearningIEEE Robotics and Automation Letters, 2023
- Motion Primitives-based Navigation Planning using Deep Collision Prediction2022
- Radio Environment Map Construction Based on Gaussian Process With Positional UncertaintyIEEE Wireless Communications Letters, 2022
- Spectrum Awareness for Cognitive Radios Supported by Radio Environment Maps: Zonal ApproachApplied Sciences, 2021
- Network Optimisation in 5G Networks: A Radio Environment Map ApproachIEEE Transactions on Vehicular Technology, 2020
- Radio Environment Maps for Dynamic Frequency Selection in V2X Communications2020
- Radio Environment Maps for Military Cognitive Networks: Deployment of Sensors vs. Map Quality2019
- Polynomial Trajectory Planning for Aggressive Quadrotor Flight in Dense Indoor Environments2016
- Cognitive radio: brain-empowered wireless communicationsIEEE Journal on Selected Areas in Communications, 2005