PolarNet: Accelerated Deep Open Space Segmentation Using Automotive Radar in Polar Domain
This addresses the need for robust perception in autonomous driving systems by improving radar-based open space segmentation, though it is incremental as it adapts deep learning to an existing sensor modality.
The paper tackles the problem of drivable space segmentation for autonomous driving by proposing PolarNet, a deep neural model that processes radar data in the polar domain, achieving state-of-the-art performance and fast processing speeds with a compact size.
Camera and Lidar processing have been revolutionized with the rapid development of deep learning model architectures. Automotive radar is one of the crucial elements of automated driver assistance and autonomous driving systems. Radar still relies on traditional signal processing techniques, unlike camera and Lidar based methods. We believe this is the missing link to achieve the most robust perception system. Identifying drivable space and occupied space is the first step in any autonomous decision making task. Occupancy grid map representation of the environment is often used for this purpose. In this paper, we propose PolarNet, a deep neural model to process radar information in polar domain for open space segmentation. We explore various input-output representations. Our experiments show that PolarNet is a effective way to process radar data that achieves state-of-the-art performance and processing speeds while maintaining a compact size.