└── README.md
/README.md:
--------------------------------------------------------------------------------
1 | # EIKF-VIO-LIO
2 |
3 | (Currently, only the necessary steps for using the code are observable. Full open access will be enabled after the review.)
4 |
5 |
6 |
7 |
8 | Table of Contents
9 |
10 | -
11 | Prerequisites
12 |
13 | -
14 | Installation
15 |
16 | -
17 | Run on datasets
18 |
19 | -
20 | Evaluation
21 |
22 | -
23 | Acknowledgement
24 |
25 | -
26 | Citation
27 |
28 |
29 |
30 |
31 |
32 | ## Prerequisites
33 |
34 | 1. Livox_ros_driver
35 |
36 | follow https://github.com/Livox-SDK/livox_ros_driver
37 |
38 | ## Installation
39 |
40 | 1. Create ROS workspace
41 |
42 | ```markdown
43 | mkdir -p ~/EIKF_LIO_VIO/src
44 | cd EIKF_LIO_VIO/src
45 | ```
46 |
47 | 2. Clone the repository and build
48 |
49 | ```markdown
50 | git clone git@github.com:LIAS-CUHKSZ/EIKF-VIO-LIO.git
51 | cd ..
52 | catkin_make
53 | ```
54 |
55 |
56 |
57 |
58 |
59 | ## Run
60 |
61 | We have tested the following datasets, which config file can be directly used. We only support the dataset type: rosbag containing lidar, IMU and camera measurements.
62 |
63 | | Datasets | Dataset link | Launch file | data preprocess | evaluation method | evaluation script |
64 | | --------------- | ------------------------------------------------------- | ----------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
65 | | URCA | https://advdataset2019.wixsite.com/urbanloco/california | URCA.launch | Rosbag with all sensors is provided, you can directly use. | evo | UR_evaluation.sh |
66 | | URHK | https://advdataset2019.wixsite.com/urbanloco/hong-kong | urbanloco.launch | Rosbag with all sensors is provided, you can directly use. | evo | UR_evaluation.sh |
67 | | NTU Viral | https://ntu-aris.github.io/ntu_viral_dataset/ | NTU_VIRAL.launch | Rosbag with all sensors is provided, you can directly use. | https://ntu-aris.github.io/ntu_viral_dataset/evaluation_tutorial.html | https://ntu-aris.github.io/ntu_viral_dataset/evaluation_tutorial.html |
68 | | NTU MCD | https://mcdviral.github.io/ | NTU_Viral2.launch | Need to merge rosbag with different topics. You can refer to : https://github.com/LIAS-CUHKSZ/DataProcessTools4SLAM/blob/main/merge_rosbag.py | evo | evaluate_ntu2.sh |
69 | | private dataset | Our hand-held device | ilive_mid.launch | Rosbag with all sensors is provided, you can directly use. | evo | lab_evaluation.sh |
70 | | | | | | | |
71 |
72 | * You can run the evaluation script directly. Evo is already included in the script.
73 | * evo: https://michaelgrupp.github.io/evo/doc/performance.html
74 | * Evaluation metric we used in evo: root-mean-square-error (rmse) of absolute pose error (ape) with translation part (evo_ape), with unit (m).
75 |
76 | 1.1 Download datasets and remember its path and the name of rosbag .
77 |
78 | 1.2 Modify the corresponding launch file.
79 |
80 | ```
81 |
82 |
83 |
84 |
85 |
86 |
87 | ```
88 |
89 | 1.3 Run the code
90 |
91 | ```
92 | source devel/setup.bash
93 | roslaunch ilive
94 | ```
95 |
96 | ## Evaluation
97 |
98 | If you want to get evaluation result, please run the corresponding evaluation script.
99 |
100 |
101 |
102 | ## Acknowledgement
103 |
104 | We thank the authors of the following repositories for their open-source code:
105 |
106 | OpenVINS:
107 | https://docs.openvins.com/
108 |
109 | Fast-LIO:
110 | https://github.com/hku-mars/FAST_LIO
111 |
112 | R3live:
113 | https://github.com/hku-mars/r3live
114 |
115 | ## Citation
116 |
117 | ```
118 | @misc{li2024efficient,
119 | title={Efficient Invariant Kalman Filter for Inertial-based Odometry with Large-sample Environmental Measurements},
120 | author={Xinghan Li and Haoying Li and Guangyang Zeng and Qingcheng Zeng and Xiaoqiang Ren and Chao Yang and Junfeng Wu},
121 | year={2024},
122 | eprint={2402.05003},
123 | archivePrefix={arXiv},
124 | primaryClass={cs.RO}
125 | }
126 | ```
127 |
--------------------------------------------------------------------------------