KAN-Powered Large-Target Detection for Automotive Radar

This article presents a novel radar signal detection pipeline focused on detecting large targets such as cars and sports utility vehicles (SUVs). Traditional methods, such as ordered-statistic constant false alarm rate (OS-CFAR), commonly used in automotive radar, are designed for point or isotropic target models. These may not adequately capture the range-Doppler (RD) scattering patterns of larger targets, especially in high-resolution radar systems. Additional modules such as association and tracking are necessary to refine and consolidate the detections over multiple dwells. To address these limitations, we propose a detection technique based on the probability density function (pdf) of RD segments, leveraging the Kolmogorov–Arnold neural network (KAN) to learn the data and generate interpretable symbolic expressions for binary hypotheses. Beside the Monte Carlo study showing better performance for the proposed KAN expression over OS-CFAR, it is shown to exhibit a probability of detection ( $P_{D}$ ) of 96% when transfer learned with field data. The false alarm rate ( $P_{\mathrm {FA}}$ ) is comparable with OS-CFAR designed with $P_{\mathrm {FA}}=10^{-6}$ . The study also examines how the number of pdf bins in the RD segment affects the performance of KAN-based detection.