基于IMU紧耦合的LeGO-LOAM改进算法研究  

Research on improved LeGO-LOAM algorithm based on IMU tight coupling

作　　者：陈文浩 刘辉席 杨林涛[1] 刘守印[1] Chen Wenhao;Liu Huixi;Yang Lintao;Liu Shouyin(College of Physical Science&Technology,Central China Normal University,Wuhan 430070,China)

机构地区：[1]华中师范大学物理科学与技术学院,武汉430070

出　　处：《计算机应用研究》2021年第4期1013-1016,共4页Application Research of Computers

基　　金：中央高校基本科研业务费资助项目(CCNU19CG006)。

摘　　要：基于LiDAR和SLAM(simultaneous localization and mapping)的LeGO-LOAM算法在低分辨率的LiDAR设备上,由于LiDAR数据的运动畸变、采样的地面数据稀疏等问题,存在重力矢量漂移现象和严重的高程估计误差。为了改善这一点,LeGO-LOAM改进算法引入了一种LiDAR和IMU(inertial measurement unit)紧耦合的方式。通过IMU估计运动状态,消除LiDAR数据的运动畸变,并使用IMU数据构建联合优化函数,约束位置姿态估计的重力方向。实验结果表明,这种方法有效抑制了LeGO-LOAM算法的重力矢量漂移,高程估计精度和高速状态下的定位精度均有显著提升。LeGO-LOAM algorithm based on LiDAR and SLAM on low-resolution LiDAR devices,due to problems such as motion distortion of the LiDAR data and sparse sampled ground data,there are gravity vector drift phenomena and serious elevation estimation errors.In order to improve this,the improved LeGO-LOAM algorithm introduced a way of tight coupling of LiDAR and IMU.It estimated the motion state through IMU,eliminated the motion distortion of LiDAR data,and constructed the joint optimization function using IMU data to constrain the direction of gravity for position and attitude estimation.The experimental results show that this method effectively suppresses the gravity vector drift of the LeGO-LOAM algorithm,and the accuracy of elevation estimation and positioning accuracy at high speeds are significantly improved.

关 键 词：实时实位与地图重建 LIDAR IMU紧耦合 LeGO-LOAM 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]