Local Map Construction with SDMap: A Comprehensive Survey

2024-09-04

AI Summary

To address challenges in intelligent driving—including difficulty in fusing multi-source sensor data, loss of environmental details, and unstable spatiotemporal alignment—when constructing high-precision, real-time local maps from Standard Definition Maps (SDMaps), this paper presents a systematic survey of SDMap-driven local mapping paradigms. We formalize the problem definition, outline a generic pipeline, analyze multimodal representation and fusion strategies, review mainstream benchmarks, and identify core bottlenecks. Methodologically, we propose three evolutionary directions: SDMap optimization, spatiotemporal alignment enhancement, and road topology reasoning; and establish a comprehensive methodology framework covering preprocessing, fusion modeling, spatial alignment, and representation learning. Our contributions clarify technical boundaries and provide both theoretical foundations and practical guidelines for robust, scalable online local map perception.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Local Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

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

Abstract

Local map construction is a vital component of intelligent driving perception, offering necessary reference for vehicle positioning and planning. Standard Definition map (SDMap), known for its low cost, accessibility, and versatility, has significant potential as prior information for local map perception. This paper mainly reviews the local map construction methods with SDMap, including definitions, general processing flow, and datasets. Besides, this paper analyzes multimodal data representation and fusion methods in SDMap-based local map construction. This paper also discusses key challenges and future directions, such as optimizing SDMap processing, enhancing spatial alignment with real-time data, and incorporating richer environmental information. At last, the review looks forward to future research focusing on enhancing road topology inference and multimodal data fusion to improve the robustness and scalability of local map perception.

Problem

• SDMap
• Smart Driving
• Information Fusion

Innovation

• SDMap
• Information Fusion
• Real-time Alignment