/MSF_LOAM

Multi-Sensor Fusion SLAM Based on A-LOAM.

Primary LanguageC++OtherNOASSERTION

MSF_LOAM ci

[toc]

Multi-Sensor Fusion SLAM

MSF_LOAM is a Multi-Sensor Fusion SLAM implementation based on A-LOAM.

Modifier Keke Liu
Paper arxiv

1. Prerequisites

1.1 Ubuntu and ROS

Recommend: Ubuntu 20.04 and ROS Noetic.

1.2. Dependencies

Ceres Solver

sudo apt install libceres-dev

PCL

sudo apt install libpcl-dev

fmt

sudo apt install libfmt-dev

2. Build MSF_LOAM

Clone the repository and catkin_make.

3. Run

3.1 Datasets

TODO

3.2 Velodyne VLP-16 Example

Download NSH indoor outdoor to YOUR_DATASET_FOLDER.

roslaunch msf_loam_velodyne msf_loam_velodyne_VLP_16.launch
rosbag play ${YOUR_DATASET_FOLDER}/nsh_indoor_outdoor.bag

3.3 Use self-collected data

Sensor ROS topic Frequency Remark
LiDAR (Required) /velodyne_points 10
GPS /odometry_gt 1
IMU /imu 400 higher frequency is better, use xsens_ros_mti_driver to record IMU data with high time precision

ATTENTION /velodyne_points must satisfy either of the following requirements:

a. The field 'time' exists by using latest velodyne ROS driver;
b. Ring increases with vertical angle and ring points are organized in CW order.

4. Acknowledgements

Thanks for LOAM (J. Zhang and S. Singh. LOAM: Lidar Odometry and Mapping in Real-time) and A-LOAM.

5. Features

DONE

  • Graph based LiDAR-GPS fusion
  • LiDAR-IMU tightly-coupled localization, step1
  • LiDAR-IMU extrinsic parameter estimation

TODO

  • LiDAR-IMU tightly-coupled localization, step2
  • Loop closure by scancontext
  • Online temporal calibration for system

6. Related paper

  • Qin, T., Li, P. and Shen, S., 2018. Vins-mono: A robust and versatile monocular visual-inertial state estimator. IEEE Transactions on Robotics, 34(4), pp.1004-1020.
  • Qin, T. and Shen, S., 2018, October. Online temporal calibration for monocular visual-inertial systems. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 3662-3669). IEEE.
  • Wu, Y., 2019. Formula Derivation and Analysis of the VINS-Mono. arXiv preprint arXiv:1912.11986.