Lane fields improve online mapping for driverless cars
Learning Lane-Structured Conditioning Fields for Online HD Mapping
Computer Vision and Pattern Recognition
Summary
High-definition maps help self-driving cars understand roads better, but existing methods either lose important lane shapes or are hard to combine with other tools. The authors created a new way called Lane Field that stores detailed lane shapes in a simple, learnable format aligned with the bird’s-eye view of the road. Their system uses these lane fields to adjust internal map features and guide attention to important lane areas, boosting accuracy. Tests show their approach improves current mapping methods for recognizing lane segments.
What this means in practice
- •For autonomous vehicle engineers: Enhance real-time HD mapping modules to produce more accurate lane shapes using onboard sensors and learned lane field conditioning.
- •For road infrastructure planners: Use lane-structured representations to evaluate and update digital road maps with local geometric details for maintenance and upgrades.
Authors
Andrea Bertogalli, Anthony Dell'Eva, Marcello Ceresini, Federico Pirazzoli, Lorenzo Cipelli, Filippo D'Addeo, Nicola Marinello, Massimo Bertozzi
Abstract
High-definition maps provide critical structural information for downstream autonomous driving tasks. Recent methods increasingly rely on external priors to improve prediction accuracy and robustness. Yet, existing prior representations expose a trade-off: dense rasters are easy to integrate but ignore certain map geometric properties, while sparse vectors preserve geometric structure but require dedicated encoders and are difficult to plug into existing architectures. Moreover, external priors can be inaccurate, costly to acquire, or difficult to maintain, motivating a structural representation that can provide geometric guidance while remaining learnable and broadly applicable. We address this limitation with the Lane Field, a dense BEV-aligned geometric representation that encodes local lane structure at each spatial location and can be either predicted from onboard observations or constructed from external map priors. Building on this representation, we introduce a plug-and-play framework that enhances online HD mapping through two complementary mechanisms: BEV feature modulation, which injects lane-structured cues into latent BEV features, and deformable attention guidance, which steers query sampling toward the underlying lane geometry. We primarily evaluate our method on OpenLane-V2, showing that conditioning BEV features and guiding deformable attention with local lane geometry enables our framework to consistently improve existing methods and achieve state-of-the-art performance on lane segment perception. Project page: https://andberto.github.io/LaneField/