Maps for Autonomous Driving: Full-process Survey and Frontiers
This is an incremental survey for researchers and practitioners in autonomous driving, summarizing existing advancements without introducing new methods.
The paper surveys the evolution of maps for autonomous driving, categorizing them into HD, Lite, and implicit maps, and reviews production workflows, technical challenges, and solutions, while exploring integration into end-to-end frameworks.
Maps have always been an essential component of autonomous driving. With the advancement of autonomous driving technology, both the representation and production process of maps have evolved substantially. The article categorizes the evolution of maps into three stages: High-Definition (HD) maps, Lightweight (Lite) maps, and Implicit maps. For each stage, we provide a comprehensive review of the map production workflow, with highlighting technical challenges involved and summarizing relevant solutions proposed by the academic community. Furthermore, we discuss cutting-edge research advances in map representations and explore how these innovations can be integrated into end-to-end autonomous driving frameworks.