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

TL;DR

This paper presents EGC-VMAP, an end-to-end framework that leverages crowdsourced vehicle data and a novel transformer architecture to generate accurate, city-scale vectorized maps efficiently, reducing manual effort significantly.

Contribution

The paper introduces a novel Trip-Aware Transformer architecture and hierarchical matching for multi-vehicle data fusion, enabling scalable, accurate city-scale mapping from crowdsourced data.

Findings

Achieves 90% reduction in manual annotation costs.

Outperforms single-vehicle baselines in accuracy and robustness.

Validated on large-scale multi-city dataset.

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.