Bench-RNR: Dataset for Benchmarking Repetitive and Non-repetitive Scanning LiDAR for Infrastructure-based Vehicle Localization

2025-09-19

AI Summary

This study systematically evaluates the performance trade-offs between repetitive and non-repetitive scanning roadside LiDAR for infrastructure-assisted vehicle localization. To this end, we introduce the first benchmark dataset supporting both scanning modes—comprising eight trajectories and 5,445 high-temporal-synchronization point-cloud frames—and publicly release both data and code. We further propose and implement the first dual-mode localization baseline, conducting comprehensive comparative experiments across multiple trajectories. Results demonstrate that non-repetitive scanning LiDAR effectively eliminates blind zones and reduces hardware cost while achieving localization accuracy and robustness on par with repetitive scanning systems. This work establishes the first standardized benchmark for evaluating roadside LiDAR scanning modalities, bridging a critical gap in the literature. It provides empirical validation and technical foundations for cost-effective, high-performance cooperative perception in intelligent transportation systems.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Vehicle localization using roadside LiDARs can provide centimeter-level accuracy for cloud-controlled vehicles while simultaneously serving multiple vehicles, enhanc-ing safety and efficiency. While most existing studies rely on repetitive scanning LiDARs, non-repetitive scanning LiDAR offers advantages such as eliminating blind zones and being more cost-effective. However, its application in roadside perception and localization remains limited. To address this, we present a dataset for infrastructure-based vehicle localization, with data collected from both repetitive and non-repetitive scanning LiDARs, in order to benchmark the performance of different LiDAR scanning patterns. The dataset contains 5,445 frames of point clouds across eight vehicle trajectory sequences, with diverse trajectory types. Our experiments establish base-lines for infrastructure-based vehicle localization and compare the performance of these methods using both non-repetitive and repetitive scanning LiDARs. This work offers valuable insights for selecting the most suitable LiDAR scanning pattern for infrastruc-ture-based vehicle localization. Our dataset is a signifi-cant contribution to the scientific community, supporting advancements in infrastructure-based perception and vehicle localization. The dataset and source code are publicly available at: https://github.com/sjtu-cyberc3/BenchRNR.

Problem

• Benchmarking repetitive vs non-repetitive LiDAR scanning patterns
• Evaluating infrastructure-based vehicle localization performance
• Addressing limited application of non-repetitive LiDAR in roadside perception

Innovation

• Benchmarking repetitive and non-repetitive scanning LiDARs
• Dataset containing 5,445 frames with diverse trajectories
• Establishing baselines for infrastructure-based vehicle localization