In this work, we propose the LiDAR Road-Atlas, a compactable and efficient 3D map representation, for autonomous robot or vehicle navigation in general urban environment. The LiDAR Road-Atlas can be generated by an online mapping framework based on incrementally merging local 2D occupancy grid maps (2D-OGM). Specifically, the contributions of our LiDAR Road-Atlas representation are threefold. First, we solve the challenging problem of creating local 2D-OGM in non-structured urban scenes based on a real-time delimitation of traversable and curb regions in LiDAR point cloud. Second, we achieve accurate 3D mapping in multiple-layer urban road scenarios by a probabilistic fusion scheme. Third, we achieve very efficient 3D map representation of general environment thanks to the automatic local-OGM induced traversable-region labeling and a sparse probabilistic local point-cloud encoding. Given the LiDAR Road-Atlas, one can achieve accurate vehicle localization, path planning and some other tasks. Our map representation is insensitive to dynamic objects which can be filtered out in the resulting map based on a probabilistic fusion. Empirically, we compare our map representation with a couple of popular map representation methods in robotics and autonomous driving societies, and our map representation is more favorable in terms of efficiency, scalability and compactness. In addition, we also evaluate localization accuracy extensively given the created LiDAR Road-Atlas representations on several public benchmark datasets. With a 16-channel LiDAR sensor, our method achieves an average global localization errors of 0.26m (translation) and 1.07 degrees (rotation) on the Apollo dataset, and 0.89m (translation) and 1.29 degrees (rotation) on the MulRan dataset, respectively, at 10Hz, which validates the promising performance of our map representation for autonomous driving.

翻译：在本文中，我们提出了一种紧凑且高效的3D地图表示方法——激光雷达道路地图集，用于自主机器人或车辆在通用城市环境中的导航。该地图集可通过一种基于增量合并局部2D占据网格地图的在线建图框架生成。具体而言，我们的激光雷达道路地图集表示方法在三个方面做出了贡献。首先，我们解决了一个具有挑战性的问题：基于激光雷达点云中可通行区域和路沿区域的实时划定，在非结构化城市场景中创建局部2D占据网格地图。其次，通过一种概率融合方案，我们实现了多层城市道路场景中的精确3D建图。第三，得益于自动局部占据网格地图引导的可通行区域标记和稀疏概率局部点云编码，我们实现了通用环境的高效3D地图表示。基于该激光雷达道路地图集，可以完成精确的车辆定位、路径规划及其他任务。我们的地图表示方法对动态物体不敏感，可通过概率融合将其从最终地图中滤除。通过实验，我们将该地图表示方法与机器人和自动驾驶领域中的多种主流地图表示方法进行了比较，结果显示，我们的地图表示方法在效率、可扩展性和紧凑性方面表现更优。此外，我们还基于在多个公开基准数据集上创建的激光雷达道路地图集，对定位精度进行了广泛评估。使用16通道激光雷达传感器，我们的方法在Apollo数据集上实现了平均全局定位误差为0.26米（平移）和1.07度（旋转），在MulRan数据集上实现了0.89米（平移）和1.29度（旋转），处理频率为10Hz，这验证了我们的地图表示方法在自动驾驶中的优异性能。