Uni-PrevPredMap: Extending PrevPredMap to a Unified Framework of Prior-Informed Modeling for Online Vectorized HD Map Construction

2025-04-09

AI Summary

To address robustness and consistency challenges in online high-definition (HD) vector map construction for autonomous driving under map-absent scenarios, this paper proposes a prior-agnostic online vectorization mapping framework. Methodologically, it introduces: (1) a tile-indexed 3D vector global map processor enabling efficient spatial indexing and incremental updates; (2) a tri-modal collaborative optimization paradigm—unifying prior-free, map-absent, and map-prior settings—to jointly integrate heterogeneous historical predictions and outdated simulation maps; and (3) dynamic multi-source prior weighting, substantially reducing reliance on ideal prior accuracy. Evaluated on mainstream online HD map benchmarks, the framework achieves state-of-the-art performance. Notably, it maintains high robustness even under severe noise in outdated map inputs, empirically validating the complementary benefits of the two prior types and demonstrating strong generalization capability.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Safety constitutes a foundational imperative for autonomous driving systems, necessitating the maximal incorporation of accessible external prior information. This study establishes that temporal perception buffers and cost-efficient maps inherently form complementary prior sources for online vectorized high-definition (HD) map construction. We present Uni-PrevPredMap, a unified prior-informed framework that systematically integrates two synergistic information sources: previous predictions and simulated outdated HD maps. The framework introduces two core innovations: a tile-indexed 3D vectorized global map processor enabling efficient refreshment, storage, and retrieval of 3D vectorized priors; a tri-mode operational optimization paradigm ensuring consistency across prior-free, map-absent, and map-prior scenarios while mitigating reliance on idealized map fidelity assumptions. Uni-PrevPredMap achieves state-of-the-art performance in map-free scenarios across established online vectorized HD map construction benchmarks. When provided with simulated outdated HD maps, the framework exhibits robust capabilities in error-resilient prior fusion, empirically confirming the synergistic complementarity between previous predictions and simulated outdated HD maps. Code will be available at https://github.com/pnnnnnnn/Uni-PrevPredMap.

Problem

• Unified framework for prior-informed online HD map construction
• Integrates temporal buffers and cost-efficient maps as complementary priors
• Ensures consistency across prior-free and map-prior scenarios

Innovation

• Unified framework integrating temporal and map priors
• Tile-indexed 3D vectorized global map processor
• Tri-mode optimization for prior-free and map scenarios