Light Detection and Ranging (LiDAR) systems play a crucial role in automotive research and various sensing-driven tasks, including navigation, 3D mapping, and environmental monitoring. A key function of LiDAR is generating point cloud data, which serves as input for Artifcial Intelligence (AI) algorithms to perform 3D object detection. However, the performance of high-fidelity 3D object detection models primarily relies on LiDAR resolution in capturing precise geometric information, especially at extended ranges. Finer resolutions yield dense point clouds, which can improve detection accuracy but, in turn, result in significantly increased data volumes and computational costs. Therefore, a trade-of between LiDAR-generated point cloud density and AI-based detection accuracy is critical for designing efficient 3D perception systems. In this study, we propose an AI-based approach to systematically investigate LiDAR configuration for an optimal design. For this, we utilize advanced simulation tools to generate synthetic point cloud data at different angular resolutions based on urban conditions and specifically examine the impact of varying LiDAR angular resolutions, ranging from fine (e.g., 0.1° × 0.1°) to coarse (e.g., 1.0° × 1.0°) on detection performance. Furthermore, we utilize the PV-RCNN algorithm to investigate how the generated point cloud densities affect 3D object detection performance on the generated data. Our findings provide practical insights into enhancing LiDAR configuration and enable engineers to select settings that balance detection capability with computational efficiency.
Orimi et al. (Thu,) studied this question.