| 227 | 0 | 46 |
| 下载次数 | 被引频次 | 阅读次数 |
使用激光雷达在动态场景下实现精确的位姿估计与地图映射是同时定位与建图(simultaneous localization and mapping, SLAM)研究领域的重要内容之一，但动态环境中物体移动会导致SLAM算法精度下降，为此提出一种低成本且可有效剔除动态影响的激光雷达SLAM算法。首先引入深度图投影，通过检测相邻时刻深度图之间的像素值波动，筛选并去除动态点云；然后进行地面点云分割，利用非地面点云的特征实现位姿估计和地图映射，利用地面点云的特征施加地面约束，限制高度漂移；最后引入回环检测矫正全局姿态。实验结果表明，与LOAM、LeGO-LOAM和SuMa算法相比，本文算法可更有效剔除动态目标，提供更优秀的定位建图效果和鲁棒性能。
Abstract：To achieve LiDAR-based precise pose estimation and mapping in dynamic environments is a big challenge in the field of simultaneous localization and mapping(SLAM).Dynamic objects can significantly interfere with a robot's environmental perception and autonomous navigation.To address the decline in SLAM accuracy caused by moving objects in dynamic environments, this study proposes a low-cost yet effective LiDAR SLAM algorithm to eliminate dynamic interference.The algorithm introduces depth map projection to identify and remove dynamic point clouds by detecting pixel value fluctuations between consecutive depth maps.Ground point cloud segmentation is then performed, leveraging non-ground point cloud features for pose estimation and mapping.Ground point cloud features are utilized to impose ground constraints, mitigating height drift.Additionally, loop closure detection is incorporated to correct global pose drift.Experimental results demonstrate that, compared to LOAM,LeGO-LOAM,and SuMa, the proposed algorithm more effectively filters out dynamic objects, delivering superior localization and mapping performance with enhanced robustness.
[1] BAI Y N,SHAO S L,ZHANG J,et al.A review of brain-inspired cognition and navigation technology for mobile robots[J].Cyborg and Bionic Systems,2024,5:0128.
[2] 郑义桀，罗健欣，陈卫卫，等.单目视觉SLAM综述[J].软件导刊，2022,21(12):242-251.ZHENG Y J,LUO J X,CHEN W W,et al.Review of monocular visual SLAM[J].Software Guide,2022,21(12):242-251.(in Chinese)
[3] CHEN K,LOPEZ B T,AGHA-MOHAMMADI A A,et al.Direct LiDAR odometry:fast localization with dense point clouds[J].IEEE Robotics and Automation Letters,2022,7(2):2000-2007.
[4] VIZZO I,GUADAGNINO T,MERSCH B,et al.KISS-ICP:in defense of point-to-point ICP:simple,accurate,and robust registration if done the right way[J].IEEE Robotics and Automation Letters,2023,8(2):1029-1036.
[5] ZHANG J,SINGH S.LOAM:Lidar odometry and mapping in real-time[C]//Robotics:Science and Systems.Berkeley,CA,USA:[s.n.],2014,2(9):1-9.
[6] 隋心，王思语，罗力，等.基于点云特征的改进RANSAC地面分割算法[J].导航定位学报，2024,12(1):106-114.SUI X,WANG S Y,LUO L,et al.Improved RANSAC ground segmentation algorithm based on point cloud features[J].Journal of Navigation and Positioning,2024,12(1):106-114.(in Chinese)
[7] 刘砚菊，晏佳华，冯迎宾.动态场景下基于视觉的SLAM技术研究[J].半导体光电，2024,45(2):327-335.LIU Y J,YAN J H,FENG Y B.SLAM based on deep learning and optical flow constraints in dynamic scenes[J].Semiconductor Optoelectronics,2024,45(2):327-335.(in Chinese)
[8] 王柯赛，姚锡凡，黄宇，等.动态环境下的视觉SLAM研究评述[J].机器人，2021,43(6):715-732.WANG K S,YAO X F,HUANG Y,et al.Review of visual SLAM in dynamic environment[J].Robot,2021,43(6):715-732.(in Chinese)
[9] HORNUNG A,WURM K M,BENNEWITZ M,et al.OctoMap:an efficient probabilistic 3D mapping framework based on octrees[J].Autonomous Robots,2013,34(3):189-206.
[10] 兰凤崇，田小强，陈吉清，等.融合语义信息与物体级几何特征的实时动态激光SLAM算法[J].汽车工程，2024,46(11):2028-2038.LAN F C,TIAN X Q,CHEN J Q,et al.Real-time dynamic laser SLAM algorithm combining object-level geometric features and semantic information[J].Automotive Engineering,2024,46(11):2028-2038.(in Chinese)
[11] 杨颖，王立勇，孙鹏，等.动态环境下激光雷达地图构建[J].计算机工程与设计，2023,44(7):2125-2131.YANG Y,WANG L Y,SUN P,et al.LiDAR map construction in dynamic environment[J].Computer Engineering and Design,2023,44(7):2125-2131.(in Chinese)
[12] 杨娜，程磊.基于高效回环检测的大场景下的SLAM算法[J].沈阳理工大学学报，2024,43(2):45-51.YANG N,CHENG L.SLAM algorithm in large scenes based on efficient loop detection[J].Journal of Shenyang Ligong University,2024,43(2):45-51.(in Chinese)
[13] 孙伟，曾豪霆，张小瑞，等.基于点云强度和地面约束的大范围激光SLAM[J].电子测量与仪器学报，2024,38(4):66-75.SUN W,ZENG H T,ZHANG X R,et al.Large scale based on point cloud strength and ground constraints Lidar SLAM[J].Journal of Electronic Measurement and Instrumentation,2024,38(4):66-75.(in Chinese)
[14] SHAN T,ENGLOT B.LeGO-LOAM:lightweight and ground-optimized lidar odometry and mapping on variable terrain[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).Madrid,Spain:IEEE,2018:4758-4765.
[15] BEHLEY J,STACHNISS C.Efficient surfel-based SLAM using 3D laser range data in urban environments[C]// Robotics:Science and System XIV.Pittsburgh,PA,USA:MIT Press,2018:1-10.
基本信息:
DOI：
中图分类号:TN958.98;TP242.6
引用信息:
[1]冯迎宾,李亚玮,王天龙等.动态场景下基于激光雷达的SLAM算法[J].沈阳理工大学学报,2025,44(05):1-7.
基金信息:
辽宁省科学技术计划项目(2023JH2/10700006)