激光雷达里程计框架的性能评估：澳大利亚植物园安南山庄案例研究
Performance Assessment of Lidar Odometry Frameworks: A Case Study at the Australian Botanic Garden Mount Annan
AI总结：
本文针对自然非结构化环境数据集缺乏的问题，在澳大利亚植物园安南山庄使用128线LiDAR等传感器采集数据，评估了COIN-LIO和LIO-SAM两种激光雷达惯性里程计框架的定位性能，发现COIN-LIO在水平面和长轨迹上精度更高。
摘要：
自动驾驶车辆正在全球各种环境中进行测试。然而，在评估代表森林或花园等自然非结构化环境的数据集方面存在明显差距。为了解决这个问题，我们提出了一项在澳大利亚植物园安南山庄进行的定位研究。该区域包含开阔的草地、铺砌的小径，以及有树木和其他物体的茂密植被区域。该数据集使用128线LiDAR传感器以及GPS和IMU读数记录，以追踪本车。本文评估了两种最先进的激光雷达惯性里程计框架COIN-LIO和LIO-SAM在此数据集上的性能。我们分析了水平和垂直维度的轨迹估计，并评估了不同距离下的相对平移和偏航误差。我们的研究结果表明，虽然这两个框架在垂直平面上表现良好，但COIN-LIO在水平平面上表现出更高的准确性，特别是在长轨迹上。相比之下，LIO-SAM在较长距离上表现出更大的漂移和偏航误差。
英文摘要：
Autonomous vehicles are being tested in diverse environments worldwide. However, a notable gap exists in evaluating datasets representing natural, unstructured environments such as forests or gardens. To address this, we present a study on localisation at the Australian Botanic Garden Mount Annan. This area encompasses open grassy areas, paved pathways, and densely vegetated sections with trees and other objects. The dataset was recorded using a 128-beam LiDAR sensor and GPS and IMU readings to track the ego-vehicle. This paper evaluates the performance of two state-of-the-art LiDARinertial odometry frameworks, COIN-LIO and LIO-SAM, on this dataset. We analyse trajectory estimates in both horizontal and vertical dimensions and assess relative translation and yaw errors over varying distances. Our findings reveal that while both frameworks perform adequately in the vertical plane, COINLIO demonstrates superior accuracy in the horizontal plane, particularly over extended trajectories. In contrast, LIO-SAM shows increased drift and yaw errors over longer distances.
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。
