多传感器融合SLAM --- 7.LIO-SAM论文解读（紧耦合的激光雷达惯性SLAM）

APS2023

已于 2023-06-03 17:08:17 修改

阅读量1.3k

点赞数

分类专栏：多传感器融合SLAM（LIDAR、IMU、相机）文章标签：激光SLAM c++ 算法人工智能

于 2023-05-28 11:52:37 首次发布

本文链接：https://blog.csdn.net/qq_41694024/article/details/130909142

版权

多传感器融合SLAM（LIDAR、IMU、相机）专栏收录该内容

18 篇文章 ¥39.90 ¥99.00

订阅专栏

超级会员免费看

LIO-SAM是一种通过GTSAM实现的紧密耦合激光雷达惯性测距框架，提供高度准确、实时的轨迹估计和地图构建。该框架基于因子图，融合多种传感器数据，包括激光雷达、IMU、GPS，通过IMU预积分、激光雷达测距、GPS因子和闭环检测进行优化。通过局部扫描匹配和关键帧选择，提高系统实时性能。文章详述了LIO-SAM的工作原理和主要贡献。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

1 论文解读

1.1 摘要部分

1.2 Introduction

1.3 LIDAR INERTIAL ODOMETRY VIAS MOOTHING AND MAPPING

1.3.1 System Overview

1.3.2 IMU Preintegration Factor

1.3.3 Lidar Odometry Factor

1 论文解读

1.1 摘要部分

We propose a framework for tightly-coupled lidar inertial odometry via smoothing and mapping（通过GTSAM优化库）, LIO-SAM, that achieves highly accurate, real-time mobile robot trajectory estimation and map-building. LIO-SAM formulates lidar-inertial odometry atop a factor graph, allowing a multitude of relative and absolute measurements, including loop closures, to be incorporated from different sources as factors into the system. The estimated motion from inertial measurement unit (IMU) pre-integration de-skews point clouds and produces an initial guess for lidar odometry