Abstract
A high-definition (HD) map is becoming an integral component of future mobility systems such as autonomous and connected vehicles. Advances in computing systems, LiDAR technologies, and vehicle communication technologies have enabled the HD map to directly treat a point cloud map (PCM), modeling road environments as LiDAR signal-level data. However, if actual road environments are changed, the PCM, modeling the environments before changes, can not be used for vehicle applications. Accordingly, the PCM has to stay up-to-date states by reflecting the environment changes continuously. This paper presents a crowd-sourcing framework to update the PCM from environment changes continuously using LiDAR and vehicle communication. Multiple intelligent vehicles installed with the LiDAR sensors download the PCM from a map server via wireless vehicle communication. To minimize the effects of environment changes, a robust localization based on a hierarchical Simultaneous Localization and Mapping (SLAM) estimates the pose (position and direction). The estimated pose is used to detect the differences between the PCM and environments, which are defined as map changes. The map changes are detected by the probabilistic and evidential theory considering the LiDAR characteristics, such as beam divergence and multi-echo. The detected map changes are uploaded to the map cloud server and merged into the PCM. The proposed crowd-sourcing framework to keep the PCM up-to-date is verified and evaluated via simulations and experiments in sites with road environment changes.
Highlights
A High-definition (HD) map is an essential component for the era of autonomous cars with more accurate and detailed data (10-20 cm accuracy) than current navigation maps [1]
The HD map can be divided into two types: a landmark-level HD map and a signal-level HD map based on light detection and ranging (LiDAR)
This paper proposes a framework for updating point cloud layers in the HD maps through crowd-sourcing of LiDAR data from multiple vehicles
Summary
A High-definition (HD) map is an essential component for the era of autonomous cars with more accurate and detailed data (10-20 cm accuracy) than current navigation maps [1]. C. Kim et al.: Updating Point Cloud Layer of HD Map Based on Crowd-Sourcing of Multiple Vehicles Installed LiDAR [12], [13], and traffic signs [14]. LiDAR measurements to update the PCM were not suitable as the crowd-sourced data because the point clouds were measured by too high prices of LiDAR sensors and were too bigger to transmit the data by wireless network communications than landmark measurements. Based on the estimated pose, the differences between the downloaded PCM and environments, which are defined as map changes, can be detected with consideration of the laser characteristics of LiDAR sensors (multi-echo and beamdivergence). The contributions of the proposed system are the following: 1) The crowd-sourcing algorithm applies both probabilistic and evidential theories to detect the map changes in the PCM, considering the LiDAR measuring characteristics (such as beam divergence and multi-echo).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
