Odyssey：一种面向GNSS拒止场景的汽车激光雷达-惯性里程计数据集
Odyssey: An Automotive Lidar-Inertial Odometry Dataset with GNSS-denied situations
AI总结：
提出Odyssey数据集，采用导航级环形激光陀螺仪RTK/INS提供高精度真值，包含36个序列和长时间GNSS拒止环境（隧道、室内停车场），用于评估LIO/SLAM系统。
摘要：
激光雷达-惯性里程计（LIO）及同时定位与建图（SLAM）系统的开发与评估需要精确的真值。全球导航卫星系统（GNSS）常作为其基础，但在遮挡环境中，由于多径效应或信号丢失，其信号可能不可靠。现有数据集通过引入惯性测量单元（IMU）测量来补偿偶发的GNSS丢失，但由于累积漂移，常用系统不允许对GNSS拒止环境进行长时间研究。因此，此类数据集的多样性有限。为弥补这一空白，我们提出了Odyssey，一个汽车LIO数据集，其特点包括：（1）基于导航级环形激光陀螺仪（RLG）的RTK/INS导出的真值，其偏置稳定性比现有汽车数据集好1到4个数量级；（2）跨不同环境的36个序列的全面收集，支持稳健且全面的评估；（3）长时间的GNSS拒止环境，包括隧道以及汽车基准测试中此前未见过的室内停车场。在此，我们的RLG系统能够在常用系统会过度漂移的场景中实现准确评估。除了为LIO提供数据外，Odyssey还通过三次轨迹重复和通过精确大地坐标集成外部地图数据来支持地点识别任务。所有数据、数据加载器和补充材料均可在线获取，网址为：https://this https URL。
英文摘要：
The development and evaluation of Lidar-Inertial Odometry (LIO) and Simultaneous Localization and Mapping (SLAM) systems requires a precise ground truth. The Global Navigation Satellite System (GNSS) is often used as a foundation for this, but its signals can be unreliable in obstructed environments due to multi-path effects or loss-of-signal. While existing datasets compensate for sporadic GNSS loss by incorporating Inertial Measurement Unit (IMU) measurements, the commonly used systems do not permit prolonged study of GNSS-denied environments due to accumulated drift. Therefore, the diversity of such datasets is limited. To close this gap, we present Odyssey, an automotive LIO dataset featuring: (1) a ground truth derived from a navigation-grade Ring Laser Gyroscope (RLG)-based RTK/INS, offering bias stability one to four orders of magnitude better than existing automotive datasets; (2) a comprehensive collection of 36 sequences across diverse environments, enabling robust and comprehensive evaluation and (3) prolonged GNSS-denied environments, including tunnels and, previously unseen in the context of automotive benchmarks, indoor parking garages. Here, our RLG-based system enables accurate evaluation in scenarios where commonly employed systems would drift excessively. Besides providing data for LIO, Odyssey also supports place recognition tasks through threefold trajectory repetition and integration of external mapping data via precise geodetic coordinates. All data, dataloader and supplementary material are available online at https://odyssey.uni-goettingen.de/ .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
