TY - JOUR
T1 - Joint Design of Radar Waveform and Detector via End-to-end Learning with Waveform Constraints
AU - Jiang, Wei
AU - Haimovich, Alexander M.
AU - Simeone, Osvaldo
PY - 2021/7/19
Y1 - 2021/7/19
N2 - The problem of data-driven joint design of transmitted waveform and detector in a radar system is addressed in this paper. We propose two novel learning-based approaches to waveform and detector design based on end-to-end training of the radar system. The first approach consists of alternating supervised training of the detector for a fixed waveform and reinforcement learning of the transmitter for a fixed detector. In the second approach, the transmitter and detector are trained simultaneously. Various operational waveform constraints, such as peak-to-average-power ratio (PAR) and spectral compatibility, are incorporated into the design. Unlike traditional radar design methods that rely on rigid mathematical models with limited applicability, it is shown that radar learning can be robustified by training the detector with synthetic data generated from multiple statistical models of the environment. Theoretical considerations and results show that the proposed methods are capable of adapting the transmitted waveform to environmental conditions while satisfying design constraints.
AB - The problem of data-driven joint design of transmitted waveform and detector in a radar system is addressed in this paper. We propose two novel learning-based approaches to waveform and detector design based on end-to-end training of the radar system. The first approach consists of alternating supervised training of the detector for a fixed waveform and reinforcement learning of the transmitter for a fixed detector. In the second approach, the transmitter and detector are trained simultaneously. Various operational waveform constraints, such as peak-to-average-power ratio (PAR) and spectral compatibility, are incorporated into the design. Unlike traditional radar design methods that rely on rigid mathematical models with limited applicability, it is shown that radar learning can be robustified by training the detector with synthetic data generated from multiple statistical models of the environment. Theoretical considerations and results show that the proposed methods are capable of adapting the transmitted waveform to environmental conditions while satisfying design constraints.
U2 - 10.1109/TAES.2021.3103560
DO - 10.1109/TAES.2021.3103560
M3 - Article
SN - 0018-9251
JO - IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
JF - IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
ER -