Online Learning-based Waveform Selection for Improved Vehicle Recognition in Automotive Radar
This addresses the challenge of real-time target identification in automotive radar systems, offering a domain-specific incremental improvement.
The paper tackles the problem of adaptive waveform selection for vehicle recognition in automotive radar by proposing a satisficing Thompson sampling approach, demonstrating through simulations that it can quickly learn effective strategies from large waveform catalogs to improve classification performance.
This paper describes important considerations and challenges associated with online reinforcement-learning based waveform selection for target identification in frequency modulated continuous wave (FMCW) automotive radar systems. We present a novel learning approach based on satisficing Thompson sampling, which quickly identifies a waveform expected to yield satisfactory classification performance. We demonstrate through measurement-level simulations that effective waveform selection strategies can be quickly learned, even in cases where the radar must select from a large catalog of candidate waveforms. The radar learns to adaptively select a bandwidth for appropriate resolution and a slow-time unimodular code for interference mitigation in the scene of interest by optimizing an expected classification metric.