High Definition Map Mapping and Update: A General Overview and Future Directions

TL;DR

This survey articulates the full lifecycle of HD map mapping and updating for autonomous driving, spanning data acquisition, preprocessing, map building, and updates. It analyzes semantic segmentation and localization techniques across camera, LiDAR, and radar, and surveys geometric, SLAM-based, and online learning approaches for map construction, including transformer-based methods like MapTR and vector-focused models like VectorMapNet. Change detection and update strategies are categorized into direct, incremental, and learning-based, with emphasis on crowdsourced data, reliability challenges, and system security. The paper highlights current challenges such as real-time performance, standardization, and security, and proposes future directions including efficient optimization and blockchain-based trust mechanisms to enable scalable, secure, and accurate online HD map maintenance.

Abstract

Along with the rapid growth of autonomous vehicles (AVs), more and more demands are required for environment perception technology. Among others, HD mapping has become one of the more prominent roles in helping the vehicle realize essential tasks such as localization and path planning. While increasing research efforts have been directed toward HD Map development. However, a comprehensive overview of the overall HD map mapping and update framework is still lacking. This article introduces the development and current state of the algorithm involved in creating HD map mapping and its maintenance. As part of this study, the primary data preprocessing approach of processing raw data to information ready to feed for mapping and update purposes, semantic segmentation, and localization are also briefly reviewed. Moreover, the map taxonomy, ontology, and quality assessment are extensively discussed, the map data's general representation method is presented, and the mapping algorithm ranging from SLAM to transformers learning-based approaches are also discussed. The development of the HD map update algorithm, from change detection to the update methods, is also presented. Finally, the authors discuss possible future developments and the remaining challenges in HD map mapping and update technology. This paper simultaneously serves as a position paper and tutorial to those new to HD map mapping and update domains.

Figures (14)

• Figure 1: General pipeline of the processes involved in HD map mapping and update sequence. Figure is created and modified based on the depictions in Wijaya2022Heo2020Herb2019Kim2021
• Figure 2: The illustration of HD map layers according to the definition derived from LDM. The figure is redrawn and modified based on depictions in AECC2020
• Figure 3: The illustration of the seven layer adaptive map architecture for autonomous driving, V2X: vehicle-to-everything. The figure is obtained from Jiang2019 work with permission from the author
• Figure 4: The mobile mapping vehicle of giant mapping companies: (a) Google. (b) Bing. (c) TomTom. (d) Here.
• Figure 5: The architecture of image segmentation networks: (a) Dilation architecture. (b) Encoder-decoder architecture. (c) Multi branch architecture. Readers interested in the comprehensive descriptions of each architecture are advised to refer to the paper individually. Figure is redrawn and modified based on depictions in Yu2021