4D Millimeter-Wave Radar in Autonomous Driving: A Survey
Zeyu Han, Jiahao Wang, Zikun Xu, Shuocheng Yang, Lei He, Shaobing Xu, Jianqiang Wang, Keqiang Li
TL;DR
The paper addresses the gap in comprehensive coverage of 4D mmWave radar for autonomous driving by delivering a theory-backed survey of signal processing, 4D elevation/doppler measurement, and calibration, followed by learning-based radar data generation and extensive coverage of perception and SLAM applications. It consolidates datasets and application algorithms, highlighting both point-cloud- and pre-CFAR-data-based methods, as well as multi-modal fusion with vision and LiDAR. Key contributions include a structured taxonomy of data generation pipelines, perception and SLAM techniques, and a forward-looking discussion on challenges such as data scarcity, standardization, and real-time processing. The work underscores the practical impact of 4D radar in robust perception and localization under adverse conditions, and it outlines concrete directions for dataset expansion, algorithm redesign, and specialized information utilization to propel the field forward.
Abstract
The 4D millimeter-wave (mmWave) radar, proficient in measuring the range, azimuth, elevation, and velocity of targets, has attracted considerable interest within the autonomous driving community. This is attributed to its robustness in extreme environments and the velocity and elevation measurement capabilities. However, despite the rapid advancement in research related to its sensing theory and application, there is a conspicuous absence of comprehensive surveys on the subject of 4D mmWave radar. In an effort to bridge this gap and stimulate future research, this paper presents an exhaustive survey on the utilization of 4D mmWave radar in autonomous driving. Initially, the paper provides reviews on the theoretical background and progress of 4D mmWave radars, encompassing aspects such as the signal processing workflow, resolution improvement approaches, and extrinsic calibration process. Learning-based radar data quality improvement methods are present following. Then, this paper introduces relevant datasets and application algorithms in autonomous driving perception, localization and mapping tasks. Finally, this paper concludes by forecasting future trends in the realm of 4D mmWave radar in autonomous driving. To the best of our knowledge, this is the first survey specifically dedicated to the 4D mmWave radar in autonomous driving.