LaneMapNet: Lane Network Recognization and HD Map Construction Using Curve Region Aware Temporal Bird's-Eye-View Perception

The construction of local HD (High Definition) Map and Lane Network with onboard sensors is critical for autonomous vechicles and facilitates downstream tasks. In contrast to previous studies that treated building HD Map and Lane Network as two individual tasks, in this paper a unified BEV (Bird's-Eye-View) perception framework is proposed with seperate decoders to realize two tasks simultaneously. In this paper, the gap between object detection and curve regression when using a DETR-like decoder is discussed and a curve region aware method is proposed to make up for the above gap. Specifically, a mechanism called Curve Region Aware Deformable Attention is designed with a bezier grid sampling module to guide the attention learning in bev features and structual loss regarding shapes of lanelines is also included. Moreover, a BEV spatial-temporal fusion method is introduced to better utilize historical features with minimal loss of spatial information. The results on NuScenes dataset show that our work has been close to or exceeded SOTAs (state-of-the-art) on both two tasks simultaneously.