• Stars
    star
    207
  • Rank 189,769 (Top 4 %)
  • Language
  • License
    GNU General Publi...
  • Created over 4 years ago
  • Updated almost 4 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Decentralized_loam

A decentralized framework for simultaneous calibration, localization and mapping with multiple LiDARs

Introduction

Decentralized_loam is the code implementation of our paper "A decentralized framework for simultaneous calibration, localization and mapping with multiple LiDARs", which is developed based on our previous work Loam-livox. Our project fuses data from multiple LiDARs in a decentralized framework, which can not only address the problem of localization and mapping, but can also online calibrate the extrinsic of 6-DoF (includes 3-DoF of rotation and 3-DoF of translation).

(A). The bird's eye-view of the maps we reconstructed in one of our experiments. The point cloud data sampled from different LiDARs are rendered with different colors. (B). The satellite image of the experiment test ground; (C~E). The detailed inspection of the area marked in dashed circle in A.

Developer: Jiarong Lin

Our related paper: our paper is accepted to IROS 2020 and is now available on Arxiv:
A decentralized framework for simultaneous calibration, localization and mapping with multiple LiDARs

Our related video: our related videos are now available on YouTube (click below image to open):

video

1. Prerequisites

1.1 Ubuntu and ROS

Ubuntu 64-bit 16.04 or 18.04. ROS Kinetic or Melodic. ROS Installation and its additional ROS pacakge:

    sudo apt-get install ros-XXX-cv-bridge ros-XXX-tf ros-XXX-message-filters ros-XXX-image-transport

NOTICE: remember to replace "XXX" on above command as your ROS distributions, for example, if your use ROS-kinetic, the command should be:

    sudo apt-get install ros-kinetic-cv-bridge ros-kinetic-tf ros-kinetic-message-filters ros-kinetic-image-transport

1.2. Ceres Solver

Follow Ceres Installation.

1.3. PCL

Our code run abnormally with the lower version of PCL (version < PCL-1.9.0 ) due to some unknown reasons (maybe some bugs), therefore we recommend you install the latest version of PCL

cd YOUR_PATH
git clone https://github.com/PointCloudLibrary/pcl
cd pcl
mkdir build
cd build
cmake ..
sudo make install -j8

2. Build

Clone the repository and catkin_make:

cd ~/catkin_ws/src
git clone https://github.com/hku-mars/decentralized_loam
cd ../
catkin_make
source ~/catkin_ws/devel/setup.bash

3. Run our example

Download Our recorded rosbag and then

roslaunch dc_loam demo.launch
rosbag play dc_loam_demo.bag

Our hardware design

Not only our codes and algorithms are of open-source, but also our hardware design. You can visit this project (https://github.com/hku-mars/lidar_car_platfrom) for more details :)

License

The source code is released under GPLv2 license.

We are still working on improving the performance and reliability of our codes. For any technical issues, please contact me via email Jiarong Lin < [email protected] >.

For commercial use, please contact Dr. Fu Zhang < [email protected] >

More Repositories

1

FAST_LIO

A computationally efficient and robust LiDAR-inertial odometry (LIO) package
C++
2,549
star
2

r3live

A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package
C++
1,958
star
3

loam_livox

A robust LiDAR Odometry and Mapping (LOAM) package for Livox-LiDAR
C++
1,435
star
4

FAST-LIVO

A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).
C++
1,086
star
5

livox_camera_calib

This repository is used for automatic calibration between high resolution LiDAR and camera in targetless scenes.
C++
863
star
6

LiDAR_IMU_Init

[IROS2022] Robust Real-time LiDAR-inertial Initialization Method.
C++
834
star
7

Point-LIO

C++
745
star
8

r2live

R2LIVE: A Robust, Real-time, LiDAR-Inertial-Visual tightly-coupled state Estimator and mapping package
C++
721
star
9

BALM

An efficient and consistent bundle adjustment for lidar mapping
C++
700
star
10

ikd-Tree

This repository provides implementation of an incremental k-d tree for robotic applications.
C++
607
star
11

ImMesh

ImMesh: An Immediate LiDAR Localization and Meshing Framework
C++
590
star
12

STD

A 3D point cloud descriptor for place recognition
C++
548
star
13

VoxelMap

[RA-L 2022] An efficient and probabilistic adaptive voxel mapping method for LiDAR odometry
C++
479
star
14

mlcc

Fast and Accurate Extrinsic Calibration for Multiple LiDARs and Cameras
C++
479
star
15

FAST-LIVO2

FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry
471
star
16

HBA

[RAL 2023] A globally consistent LiDAR map optimization module
C++
437
star
17

IKFoM

A computationally efficient and convenient toolkit of iterated Kalman filter.
C++
420
star
18

M-detector

C++
362
star
19

LTAOM

C++
325
star
20

ROG-Map

C++
294
star
21

MARSIM

MARSIM: A light-weight point-realistic simulator for LiDAR-based UAVs
C++
283
star
22

D-Map

D-Map provides an efficient occupancy mapping approach for high-resolution LiDAR sensors.
C++
280
star
23

joint-lidar-camera-calib

Joint intrinsic and extrinsic LiDAR-camera calibration.
C++
194
star
24

SLAM-HKU-MaRS-LAB

In this repository, we present our research works of HKU-MaRS lab that related to SLAM
191
star
25

Voxel-SLAM

C++
185
star
26

Swarm-LIO2

Swarm-LIO2: Decentralized, Efficient LiDAR-inertial Odometry for UAV Swarms
158
star
27

dyn_small_obs_avoidance

C++
154
star
28

IPC

Integrated Planning and Control for Quadrotor Navigation in Presence of Sudden Crossing Objects and Disturbances
C++
147
star
29

btc_descriptor

137
star
30

PULSAR

C++
102
star
31

lidar_car_platfrom

48
star
32

iBTC

39
star
33

crossgap_il_rl

Python
38
star
34

multi_lidar_calib

28
star
35

Livox_handheld

25
star
36

mapping_eval

2
star