Deployable Model of Roadside Multiple Localization Systems on Expressways 2020-01-5232
Vehicle localization is an important part for the sensing function of automated driving. Previous studies can perceive the localization of vehicle based on the on-board lidar and camera with transformations of coordinated system. However, these vision-based and lidar-based localization methods have the complicated transformation calculations of coordinated system and on-board localization devices easily cause the errors arising from the vibration during the driving process. To address such a problem, a new solution of roadside localization-based method can be proposed with a core idea of these sensing devices implemented into the roadside. Firstly, the working mechanism of two localization system including vision-based and lidar-based is described, and the implementation steps can be further proposed for improve the performance of vehicle localization. A deployable model of roadside sensing devices is formulated to solve the deployment problems of multiple localization system. Moreover, multiple methods (i.e. exact algorithms, approximation algorithms or heuristic algorithms) can be used to find the optimal solutions for the proposed model. The study can effectively provide a new solution from the aspects of roadside localization and formulate a deployment model potentially be implemented in the future.