Roadside LiDAR Deployment Optimization for Vehicle-to-Infrastructure Cooperative Perception in Urban Occlusion Environments

Abstract

Roadside light detection and range sensor (LiDAR) is a way to enhance the perception capabilities of connected autonomous vehicles (CAVs) using the vehicle-to-infrastructure (V2I) cooperation system by providing complementary and beyond visual range information. However, occlusion remains challenging in roadside LiDAR required to be considered in deployment. Therefore, this article proposes a roadside LiDAR deployment optimization framework that considers the spatial-temporal occlusion arising from vehicles on urban streets. First, a pose deployment optimization model was constructed to maximize the utilization of the laser beams and minimize the spatial-temporal occlusion. Also, a network deployment problem was formulated considering the coverage intensity and cost performance with the pose deployment constraints. Then, a stagewise greedy algorithm combined with a particle swarm optimization (GA-PSO) algorithm was proposed and an elitist preservation genetic algorithm (EGA) was improved to optimize the roadside LiDAR layout and pose in the traffic network. Experiment results showed that the detection accuracy of the proposed method can reach 90.6%, outperforming current methods in different traffic conditions. Furthermore, the proposed method enables more complete target point cloud outlines capturing under various traffic and occlusion conditions.