PCLane: Accurate Lane Localization with LiDAR and abstract data

Kurzfassung

Accurate Lane localization is one of the fundamental tasks for autonomous driving and trajectory planning for precise control. Deep learning models are more suitable for accurate and precise lane detection and segmentation considering their scope for generalizations especially in complex urban scenarios like junctions and intersections. This paper presents a deep learning framework for LiDAR point cloud segmentation-based lane detection and accurate lane localization using abstract map data. This paper highlights a self-supervised training strategy for the deep neural network model using abstract High Definition OpenDRIVE maps to detect and segment lanes from the lidar point cloud data. PointNet based architecture was used as the backbone of the deep neural network model and the LiDAR point clouds were collected using Velodyne LiDAR sensor of the DLR Experimental Autonomous Driving Vehicle ViewCar2.