论文标题
Planeslam：基于飞机的LIDAR SLAM，用于在结构化3D环境中运动计划
PlaneSLAM: Plane-based LiDAR SLAM for Motion Planning in Structured 3D Environments
论文作者
论文摘要
激光雷达传感器是在未知环境中同时定位和映射（SLAM）的强大工具，但是它们产生的原始点云是密集的，计算量昂贵，并且不适合下游自主任务（例如运动计划）直接使用。为了与运动计划集成，希望大满贯管道生成轻量级的几何图表示。这样的表示也特别适合人造环境，通常可以将其视为在笛卡尔网格上建造的所谓“曼哈顿世界”。在这项工作中，我们为曼哈顿世界环境提出了一种3D LiDAR SLAM算法，该算法从点云中提取平面特征，以实现轻巧，实时的定位和映射。我们的方法生成基于平面的地图，其内存占其位置的记忆力明显少得多，并且适合于快速碰撞检查运动计划。通过利用曼哈顿世界的假设，我们靶向正交平面的提取，以生成比现有基于平面的激光雷尔大满贯方法更结构化和组织的地图。我们证明了我们在高保真的Airsim模拟器以及配备有速脂激龙的地面流动站的现实实验中的方法。在这两种情况下，我们都能以匹配10 Hz的传感器速率的速率生成高质量的图和轨迹估计值。
LiDAR sensors are a powerful tool for robot simultaneous localization and mapping (SLAM) in unknown environments, but the raw point clouds they produce are dense, computationally expensive to store, and unsuited for direct use by downstream autonomy tasks, such as motion planning. For integration with motion planning, it is desirable for SLAM pipelines to generate lightweight geometric map representations. Such representations are also particularly well-suited for man-made environments, which can often be viewed as a so-called "Manhattan world" built on a Cartesian grid. In this work we present a 3D LiDAR SLAM algorithm for Manhattan world environments which extracts planar features from point clouds to achieve lightweight, real-time localization and mapping. Our approach generates plane-based maps which occupy significantly less memory than their point cloud equivalents, and are suited towards fast collision checking for motion planning. By leveraging the Manhattan world assumption, we target extraction of orthogonal planes to generate maps which are more structured and organized than those of existing plane-based LiDAR SLAM approaches. We demonstrate our approach in the high-fidelity AirSim simulator and in real-world experiments with a ground rover equipped with a Velodyne LiDAR. For both cases, we are able to generate high quality maps and trajectory estimates at a rate matching the sensor rate of 10 Hz.
