🤖 AI Summary
To address data incompleteness and degraded long-range performance in online high-definition (HD) map construction from onboard sensors—caused by occlusions and adverse weather—this paper proposes a robust mapping method leveraging multi-source prior maps (OSM SD maps, outdated HD maps, and historical vehicle-side maps). Our approach introduces three key innovations: (1) HPQuery, a hybrid prior representation that uniformly encodes heterogeneous map elements; (2) the Unified Vector Encoder (UVE), integrating mixed-prior embeddings with a two-stage encoding mechanism; and (3) the first segment-level and point-level joint self-supervised pretraining strategy. Compatible with mainstream vectorized map representation frameworks, our method achieves significant improvements in online map prediction accuracy and robustness across three major benchmarks—nuScenes, Argoverse 2, and OpenLane-V2. It effectively mitigates single-sensor perception limitations and enhances navigation reliability for autonomous driving.
📝 Abstract
High-Definition Maps (HD maps) are essential for the precise navigation and decision-making of autonomous vehicles, yet their creation and upkeep present significant cost and timeliness challenges. The online construction of HD maps using on-board sensors has emerged as a promising solution; however, these methods can be impeded by incomplete data due to occlusions and inclement weather. This paper proposes the PriorDrive framework to addresses these limitations by harnessing the power of prior maps, significantly enhancing the robustness and accuracy of online HD map construction. Our approach integrates a variety of prior maps, such as OpenStreetMap's Standard Definition Maps (SD maps), outdated HD maps from vendors, and locally constructed maps from historical vehicle data. To effectively encode this prior information into online mapping models, we introduce a Hybrid Prior Representation (HPQuery) that standardizes the representation of diverse map elements. At the core of PriorDrive is the Unified Vector Encoder (UVE), which employs hybrid prior embedding and a dual encoding mechanism to process vector data. Furthermore, we propose a segment-level and point-level pre-training strategy that enables the UVE to learn the prior distribution of vector data, thereby improving the encoder's generalizability and performance. Through extensive testing on the nuScenes, Argoverse 2 and OpenLane-V2, we demonstrate that PriorDrive is highly compatible with various online mapping models and substantially improves map prediction capabilities. The integration of prior maps through the PriorDrive framework offers a robust solution to the challenges of single-perception data, paving the way for more reliable autonomous vehicle navigation.