Optimizing LiDAR Placements for Robust Driving Perception in Adverse Conditions

arXiv:2403.17009v1 Announce Type: new
Abstract: The robustness of driving perception systems under unprecedented conditions is crucial for safety-critical usages. Latest advancements have prompted increasing interests towards multi-LiDAR perception. However, prevailing driving datasets predominantly utilize single-LiDAR systems and collect data devoid of adverse conditions, failing to capture the complexities of real-world environments accurately. Addressing these gaps, we proposed Place3D, a full-cycle pipeline that encompasses LiDAR placement optimization, data generation, and downstream evaluations. Our framework makes three appealing contributions. 1) To identify …

abstract arxiv complexities cs.cv cs.ro data datasets driving however lidar perception robust robustness safety safety-critical systems type world