High-Resolution Range-Doppler Imaging from One-Bit PMCW Radar via Generative Adversarial Networks

Digital modulation schemes such as phase-modulated continuous wave (PMCW) have recently attracted increasing attention as possible replacements for frequency-modulated continuous wave (FMCW) modulation in future automotive radar systems. A significant obstacle to their widespread adoption is the expensive and power-consuming analog-to-digital converters (ADCs) required at gigahertz frequencies. To mitigate these challenges, employing low-resolution ADCs, such as one-bit, has been suggested. Nonetheless, using one-bit sampling results in the loss of essential information. This study explores two rangeDoppler (RD) imaging methods in PMCW radar systems utilizing neural networks (NNs). The first method merges standard RD signal processing with a generative adversarial network (GAN), whereas the second method uses an end-to-end (E2E) strategy in which traditional signal processing is substituted with an NNbased RD module. The findings indicate that these methods can substantially improve the probability of detecting targets in the range-Doppler domain.