LIDAROC dataset 20m: Realistic LiDAR Cover Contamination Dataset for Enhancing Autonomous Vehicle Perception Reliability.

Keywords: LiDAR Point Cloud corruption, Sensor phenomena, anomaly, autonomous vehicle, contamination, dataset, object detection benchmark, perception robustness testing, sensor. LiDAR is the foundation of many autonomous vehicle perception systems, so it is essential to study and ensure the integrity and robustness of the data collected by LiDAR. To facilitate future research into robust and resilient LiDAR processing, we present a dataset containing a collection of uncontaminated and realistically contaminated LiDAR samples. This dataset is the 20m dataset, which is part of the larger LIDAROC dataset. The experiment was conducted in two environments: The first was a subterranean narrow hallway with the target approximately 5 meters away, referred to as the 5m dataset, simulating a complex urban driving scenario. The second environment was a spacious outdoor area with two distance variations (10 and 20 meters). For the 5m and 10m datasets, please refer to the link below: LIDAROC 5m LIDAROC 10m关键词：激光雷达点云损坏（LiDAR Point Cloud corruption）、传感器现象（Sensor phenomena）、异常（anomaly）、自动驾驶汽车（autonomous vehicle）、污染（contamination）、数据集（dataset）、目标检测基准（object detection benchmark）、感知鲁棒性测试（perception robustness testing）、传感器（sensor）。 激光雷达（LiDAR）是诸多自动驾驶汽车感知系统的核心支撑基础，因此研究并保障激光雷达采集数据的完整性与鲁棒性具有重要意义。为推动面向鲁棒且可靠的激光雷达处理技术的后续研究，我们发布了一个包含未污染真实激光雷达样本与模拟真实污染场景的激光雷达样本集。 本数据集为20米数据集，属于更大规模的LIDAROC数据集的组成部分。 本次实验设置了两类实验环境：其一为地下狭窄走廊，目标物距离约5米，该子集被命名为5米数据集，用于模拟复杂城市驾驶场景；其二为开阔室外区域，包含两种距离工况（10米与20米）。 关于5米与10米数据集，请参阅以下链接： LIDAROC 5米 LIDAROC 10米