1 Engineering Research Center of Intelligent Rehabilitation Device and Detection Technology, Ministry of Education, Hebei University of Technology, Tianjin 300401, China
2 Hebei Key Laboratory of Robot Perception and Human-Machine Integration, Tianjin 300401, China
3 Introduction of the National Research Center for Rehabilitation Technical Aids, Beijing 100176, China
Show less
文章历史+
Received
Published
Revised
2025-02-18
2028-07-28
2025-10-20
Online Date
2026-09-20
PDF (11263K)
摘要
为了改进传统图优化建图算法在建图时环境检测能力差、特征提取不明显以及累积误差大等问题,提出一种激光与视觉融合的改进图优化建图算法。首先,标定激光雷达与深度相机,完成数据处理与融合初步消除传感器误差与数据冗余;其次,采用引入距离评价函数的协方差分析(principal component analysis,PCA)方法并结合自适应阈值设定方法选取点云特征点;然后,使用IMU(inertial measurement unit)预积分技术获得初始位姿变换矩阵完成初步扫描匹配,在此基础上采用点对面ICP(iterative closest point)算法完成最终扫描匹配,得到最终位姿变换矩阵;最后,采用蒙特卡洛定位(Monte Carlo localization,MCL)方法并结合里程计数据完成回环检测,消除累积误差。使用智能轮椅在实际场景进行建图验证,结果表明提出的改进图优化算法相比于传统图优化算法有更好的环境检测能力,并且在大环境可以有效减少累积误差,相比于传统图优化算法有一定的改进与提升。
Abstract
An improved graph optimization-based mapping algorithm was proposed to address the limitations of traditional graph optimization methods, including poor environmental perception, indistinct feature extraction, and large cumulative errors. In this approach, a LiDAR and a depth camera was first calibrated, and their data was processed and fused to preliminarily reduce sensor errors and data redundancy. A distance evaluation function was then incorporated into principal component analysis (PCA), and an adaptive threshold was set to select point cloud feature points. The initial pose transformation matrix was obtained using IMU pre-integration for preliminary scan matching, after which a point-to-plane iterative closest point (ICP) algorithm was applied to derive the final pose transformation matrix. Loop closure detection was performed using Monte Carlo localization (MCL) combined with odometry data to eliminate cumulative errors. Experiments were conducted using a smart wheelchair in real-world scenarios. The results indicate that the proposed algorithm exhibits superior environmental perception compared to traditional graph optimization methods and effectively reduces cumulative errors in large-scale environments, demonstrating noticeable improvements over conventional approaches.
近年来,随着人口老龄化趋势日益明显,智能轮椅作为一种代步工具,对提高老年人的生活质量和独立性至关重要[1-2]。智能轮椅搭载老年人在陌生环境中自主运行时,安全问题是首要的,这就必然需要一种关键技术,即同时定位与建图(simultaneous localization and mapping,SLAM)。SLAM技术是利用轮椅上携带的传感器获取环境信息,并对自身位姿进行估计构建出全局地图[3],是实现路径规划与自主导航的重要前提。
YuXinping, LuBoyang. Active measures for current situation of population aging in China[J]. China Economist, 2023, 408(2): 21-22.
[3]
袁源强. 智能轮椅室内建图及自动导航技术研究[D]. 哈尔滨: 哈尔滨工业大学, 2017.
[4]
YuanYuanqiang. Research on mapping and automated navigation in indoor environment for intelligent wheelchair[D]. Harbin: Harbin Institute of Technology, 2017.
[5]
SmithR C, CheesemanP. On the representation and estimation of spatial uncertainty[J]. International Journal of Robotics Research, 1986, 5(4): 56-68.
ZhangWeiwei, ChenChao, XuJun. Localization and mapping method of fusion laser and visual point cloud information[J]. Computer Applications and Software, 2020, 37(7): 114-119.
LuJun, ZhaoHonxu, WangWei, et al. Point cloud registration method based on key point extraction with small overlap[J]. Transactions of Beijing Institute of Technology, 2020, 40(4): 409-415.
LiuChang, DangShuwen, ChenLi. Improved pose estimation for dense mapping based on ORB-SLAM[J]. Science Technology and Engineering, 2024, 24(7): 2782-2789.
XuXiaosu, GaoJiayu, ZhouShuai, et al. Lidar-inertial SLAM based on improved GICP registration[J]. Journal of Chinese Inertial Technology, 2023, 31(8): 814-822.
YanPu, CaoHaoyu, LeiWeihao. Laser SLAM algorithm based on improved graph optimization[J]. Journal of Anhui University (Natural Science Edition), 2023, 47(4): 35-41.
JiangWenfei, ZhangXiaojun, WangJingang. Radar and camera fusion real-time positioning and mapping of underground garage[J]. Science Technology and Engineering, 2022, 22(6): 2334-2342.
ChiDexia, WangYang, NingLiqun, et al. Experimental research of camera calibration based on Zhang’s method[J]. Journal of Chinese Agricultural Mechanization, 2015, 36(2): 287-289, 337.
ChenHuawei, YuanXiaocui, WuLushen, et al. Automatic extraction of point cloud feature lines based on curvature mutation analysis[J]. Optics and Precision Engineering, 2019, 27(5): 1218-1228.