Currently, reinforcement learning (RL) has been applied for the multitarget detection task of multiple-input–multiple-output (MIMO) radars. However, the existing methods still have two shortcomings: first, the detection performance on weak targets is insufficient, and second, the solving time of the beam optimization scheme (BOS) is long. For the first issue, this article first proposes a partially time-varying statistic vector, which can more robustly distinguish the target cell from clutter cell during the “action” step of RL. Second, considering the scenario where both strong and weak targets exist, a BOS with strong target limitation is proposed, which aims to limit the power gain of beampattern on strong targets. Third, considering the scenario with all weak targets, the search mode of radar is given, and its corresponding BOS is designed. The aim is to search for possible weak targets by raising the power gain within a part of the observation area. For the second issue, by introducing a multirank beamformer, the existing and proposed BOSs are transformed into corresponding convex minimax constraint optimization problems, and their closed-form solutions are derived. Accordingly, a fast solution method is proposed. By combining the above-mentioned improvements with the Markov decision process model of MIMO radar, as well as the quasi $\varepsilon $-greedy policy and the optimized reward mechanism in existing methods, the proposed method is given. Sufficient experiments verify that the proposed improvements are valid, and that the proposed method owns better detection performance compared with its competitors.
Reinforcement Learning-Based Multitarget Detection Method for MIMO Radar via Multirank Beamformer
IEEE Transactions on Aerospace and Electronic Systems ; 61 , 3 ; 7686-7709
2025-06-01
5336754 byte
Article (Journal)
Electronic Resource
English