End-to-End Generation of City-Scale Vectorized Maps by Crowdsourced Vehicles

2025-07-11

AI Summary

High-precision city-scale vector map construction faces dual bottlenecks: prohibitive cost of traditional LiDAR-based approaches and poor robustness of single-vehicle perception methods. Method: This paper proposes an end-to-end vectorized map generation framework leveraging crowdsourced, multi-vehicle, multi-temporal perception data. Its core innovation is the Trip-Aware Transformer architecture, which enables unified modeling and fusion of cross-vehicle and cross-temporal perception outputs via hierarchical spatiotemporal matching and multi-objective joint optimization. Contribution/Results: Evaluated on a large-scale real-world multi-city dataset, the method significantly outperforms single-vehicle baselines in vector map accuracy, with substantial improvements in structural completeness and geometric fidelity. It reduces manual annotation effort by 90%, achieving both high efficiency and strong generalization. The framework establishes a novel paradigm for low-cost, scalable, high-precision urban mapping.

Technology Category

• Computer Vision: Multi-modal Vision
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Multimodal Perception & Sensor Fusion

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: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

High-precision vectorized maps are indispensable for autonomous driving, yet traditional LiDAR-based creation is costly and slow, while single-vehicle perception methods lack accuracy and robustness, particularly in adverse conditions. This paper introduces EGC-VMAP, an end-to-end framework that overcomes these limitations by generating accurate, city-scale vectorized maps through the aggregation of data from crowdsourced vehicles. Unlike prior approaches, EGC-VMAP directly fuses multi-vehicle, multi-temporal map elements perceived onboard vehicles using a novel Trip-Aware Transformer architecture within a unified learning process. Combined with hierarchical matching for efficient training and a multi-objective loss, our method significantly enhances map accuracy and structural robustness compared to single-vehicle baselines. Validated on a large-scale, multi-city real-world dataset, EGC-VMAP demonstrates superior performance, enabling a scalable, cost-effective solution for city-wide mapping with a reported 90% reduction in manual annotation costs.

Problem

• High-cost LiDAR-based city mapping needs affordable alternative
• Single-vehicle perception lacks accuracy in adverse conditions
• Scalable crowdsourced mapping requires robust multi-vehicle fusion

Innovation

• End-to-end framework for city-scale vectorized maps
• Trip-Aware Transformer fuses multi-vehicle data
• Hierarchical matching reduces manual annotation costs