多传感器融合的室内机器人SLAM  

Indoor Robot SLAM with Multi-Sensor Fusion

作　　者：徐淑萍[1] 杨定哲 熊小墩 XU Shuping;YANG Dingzhe;XIONG Xiaodun(School of Computer Science and Engineering,Xi’an Technological University,Xi’an 710021,China)

机构地区：[1]西安工业大学计算机科学与工程学院,西安710021

出　　处：《西安工业大学学报》2024年第1期93-103,共11页Journal of Xi’an Technological University

摘　　要：为了解决基于二维激光雷达的SLAM在室内环境中存在定位误差较大和建图不完善的问题,提出一种多传感器融合的室内机器人SLAM算法。该算法针对传统ICP算法在激光SLAM前端存在误匹配问题,采用更适合室内环境的PL-ICP算法,并利用扩展卡尔曼滤波融合轮式里程计和IMU为其提供初始的运动估计值。在建图阶段利用深度相机获取的三维点云数据转化的伪二维激光数据和二维激光雷达获取的数据进行融合,弥补二维激光雷达建图没有垂直方向视野的缺陷。实验结果表明:融合里程计数据相比于单一轮式里程计定位精度至少提升了33%,为PL-ICP算法提供了更高精度的初始迭代值。同时融合建图弥补了单一二维激光雷达建图的缺陷,构建了环境信息更加完善的环境地图。In order to solve the problem of large positioning error and incomplete mapping of SLAM based on two dimensional lidar in indoor environment,the paper presents a multi sensor fusion SLAM algorithm for indoor robots.For the mismatch of the traditional ICP algorithm in the front end of the lidar SLAM,the PL ICP algorithm is adopted that is more suitable for the indoor environment,and the extended Kalman filter is used to fuse the wheel odometer and IMU to provide the initial motion estimation value.During the mapping phase,the pseudo 2D laser data converted from the 3D point cloud data obtained by the depth camera is fused with the data obtained from the 2D lidar to remedy the defect that there is no vertical field of view in the 2D lidar mapping.The final experimental results show that the fusion odometer data has improved the positioning accuracy by at least 33%compared to a single wheeled odometer,providing a higher initial iteration value for the PL ICP algorithm.And also,fusion mapping compensates for the weakness that a single two dimensional lidar mapping has,and constructs an environmental map with more complete environmental information.

关 键 词：同步定位与建图 室内机器人 扩展卡尔曼滤波 PL-ICP算法 

分 类 号：TP273.5[自动化与计算机技术—检测技术与自动化装置]