Reinforcement Learning-Based MIMO Radar Multitarget Detection Assisted by Bayesian Inference
- 29 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (4) , 4463-4478
Abstract
Reinforcement Learning (RL) has been used to implement the perception-action cycle of multi-input-multi-output (MIMO) cognitive radar (CR). This allows for the adaptive optimization of the radar's beampattern, which is guided by information from echoes and an appropriate reward signal. However, the present approaches rely on a greedy DOA estimation to select candidate angles, which means that decisions are primarily based on detection results from the last pulse. If the system misses a target, it can be time-consuming to recapture it, and this can limit the detection performance. To address this issue, we develop a data-driven method for executing DOA estimation by utilizing the Bayesian inference to evaluate the likelihood of an angle containing a target based on historical detection information. Furthermore, to accommodate dynamic scenarios, a decay method for historical experience is proposed, allowing the system to adapt to environmental changes dynamically. The simulation results show that the RL-based MIMO radar with our refined DOA estimation module outperforms existing RL-based detector, providing the SOTA detection performance by focusing more frequently on essential angles, even in small-scale system setups.Keywords
Funding Information
- National Natural Science Foundation of China (U23A20274, 12201523, 62131016)
- Natural Science Foundation of Sichuan Province (24NSFTD0101)
This publication has 31 references indexed in Scilit:
- Improved Neyman-Pearson Network for MIMO Radar Moving Target Detection2022
- Data-driven transmit weight matrix design method for target detection of the TS-FDA-MIMO radarExpert Systems with Applications, 2022
- Weak Target Detection in Massive MIMO Radar via an Improved Reinforcement Learning Approach2022
- Joint detection threshold adjustment and power allocation strategy for cognitive MIMO radar target trackingDigital Signal Processing, 2022
- Machine Learning and Deep Learning Techniques for Colocated MIMO Radars: A Tutorial OverviewIEEE Access, 2021
- End-to-end Learning of Waveform Generation and Detection for Radar Systems2019
- Reinforcement learning-based waveform optimization for MIMO multi-target detection2018
- Parallel and distributed methods for nonconvex optimization2014
- Cognitive Radar: Step Toward Bridging the Gap Between Neuroscience and EngineeringProceedings of the IEEE, 2012
- Target Tracking in Interference Environments Reinforcement Learning and Design for Cognitive Radar Soft Processing2008