Skip to content

zhexin1904/EECE5550Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Dependency

LeGO-LOAM:

  • ROS Noetic
  • GTSAM 4.00-alpha2
  • PCL
  • OpenCV

GNSS process:

  • Geographiclib (used for LLA to local Cartesian frame conversion)

Visualization on Google Map:

Some packages are required for utbm dataset will be listed on Dataset section

Build

cd ~/catkin_ws/src
git clone https: https://github.com/zhexin1904/EECE5550Project.git
cd ..
catkin_make -j

Dataset

image

Dependency:

  • (used to process the GNSS data of utbm dataset)

magellan_proflex500_driver

utbm_nmea_msgs

  • You may need Velodyne(Used to convert raw Velodyne data packets to sensor_msgs/PointCloud2)
  • velodyne_pointcloud(If you are also using Noetic, there might be errors due to missing functions. Please consider using a lower version of the library.)

image

Dependency:

Usage

run in utbm

# cd your workspace
source devel/setup.bash
roslaunch lego_loam lego_loam_utbm.launch

run in Mulran

# cd your workspace
source devel/setup.bash
roslaunch lego_loam lego_loam_mulran.launch 

Evaluation

trajectory

Using evo to evaluate the trajectory (ATE, RTE...)

For utmb, groundtruth need to subscribe GNSS message, and convert to TUM fomart(our code provided)

For Mulran, please access the groundtruth in their webpage

pcd map

Here, we use a simple way to save the pcd map:

  • record the global map message in a ros bag, when the dataset is almost over
  • using pcl_ros to convert rosbag to pcd

Configure your dataset!

Besides the basic config of Lidar SLAM(point cloud topic, Lidar type, imu topic......) in utility_legoLoam.h, (may be will convert a better config format :) , like yaml) for our GPS-module , several configuration need to do in:

gpsTopic(your gps topic)

gpsCovThreshold(a manually set threshold to reject bad gps measurement)

gpsFrequence(used in synchronization, but not need to set really strictly)

......

Acknowledgement

This work is built based on LeGO-LOAM

Thanks for these great works from which we learned and used to build the system:

LIO-SAM

hdl_graph_slam

LIO_SAM_6AXIS

About

The final project of EECE5550

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published