Abstract
Autonomous driving is experiencing rapid development. A lane-level map is essential for autonomous driving, and a lane-level road network is a fundamental part of a lane-level map. A large amount of research has been performed on lane-level road network generation based on various on-board systems. However, there is a lack of analysis and summaries with regards to previous work. This paper presents an overview of lane-level road network generation techniques for the lane-level maps of autonomous vehicles with on-board systems, including the representation and generation of lane-level road networks. First, sensors for lane-level road network data collection are discussed. Then, an overview of the lane-level road geometry extraction methods and mathematical modeling of a lane-level road network is presented. The methodologies, advantages, limitations, and summaries of the two parts are analyzed individually. Next, the classic logic formats of a lane-level road network are discussed. Finally, the survey summarizes the results of the review.
Highlights
An autonomous vehicle that is equipped with sensors, controllers, and other devices can drive by itself efficiently and safely
A laser scanner is appropriate for extracting the high precision of a lane-level road network, but it costs a large amount and it can be affected by bad weather such as snow or fog
Chapters review lane-level road geometry extraction methods, and it is divided into three parts based on different data sources for the methods
Summary
An autonomous vehicle that is equipped with sensors, controllers, and other devices can drive by itself efficiently and safely. Navigation electrical maps and road-level maps have been widely used in the automotive field These maps are insufficient for both the context of lane information and the accuracy of the lane and segment geometry. Lane-level maps are enhanced with lane-level details of the environment for autonomous driving compared with road-level maps. Since lane-level maps support autonomous driving safety and flexibility, a critical review of the lane-level road network of a lane-level map is presented in this paper. A lane-level map includes a lane-level road network, lane-level attribution in detail, and lane geometry lines with high accuracy, from the 10 cm level to the decimeter level modeling the real world. We discuss the lane-level road geometry extraction methods of a lane-level road network for autonomous driving. We provide a discussion and conclusions of this work
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have