Awesome

M2DGR： a Multi-modal and Multi-scenario SLAM Dataset for Ground Robots （RA-L & ICRA2022）

💎 First Author: Jie Yin 殷杰   📝 [Paper]   ➡️ [Dataset Extension]   ⭐️[Presentation Video]

🎯 Notice

We strongly recommend that the newly proposed SLAM algorithm be tested on our M2DGR / M2DGR-plus / Ground-Challenge / SJTU-GVI benchmark, because our data has following features:

1. Rich sensory information including vision, lidar, IMU, GNSS,event, thermal-infrared images and so on
2. Various scenarios in real-world environments including lifts, streets, rooms, halls and so on.
3. Our dataset brings great challenge to existing cutting-edge SLAM algorithms including LIO-SAM and ORB-SLAM3. If your proposed algorihm outperforms these SOTA systems on our benchmark, your paper will be much more convincing and valuable.
4. 🔥 Extensive excellent open-source projects have been built or evaluated on M2DGR/M2DGE-plus so far, for examples, Ground-Fusion, LVI-SAM-Easyused, MM-LINS, Log-LIO, LIGO, Swarm-SLAM, VoxelMap++, GRIL-Cali, LINK3d, i-Octree, LIO-EKF, Fast-LIO ROS2, HC-LIO, LIO-RF, PIN-SLAM, LOG-LIO2, Section-LIO, I2EKF-LO, Liloc, BMBL, Light-LOAM and so on!

Table of Contents

1. 🚩 News & Updates
2. Introduction
   • Abstract
   • Main Contributions
   • Video
3. License
4. Sensor Setup
   • Acquisition Platform
   • Sensor Parameters
5. ⭐️ Dataset Sequences
   • Outdoors
   • Indoors
   • Alternative Indoors and Outdoors
6. 📝 Configuration Files
7. Development Toolkits
   • Extracting Images
   • Evaluation
   • Calibration
   • Getting RINEX Files
   • ROS Drivers for UVC Cameras
8. Star History
9. Acknowledgement

[!TIP] Check the table of contents above for a quick overview. And check the below news for lateset updates, especially the list of projects based on M2DGR.

News & Updates

• 2024/07/15: Introducing a list of LiDAR-Visual SLAM systems at awesome-LiDAR-Visual-SLAM, wheel-based SLAM systems at awesome-wheel-slam, and Isaac Sim resources at awesome-isaac-sim (keep updating)

• 🔥2024/05/16: Introducing a list of excellent projects based on M2DGR dataset: (keep updating)

  • Dataset extension: Ground-Fusion: A Low-cost Ground SLAM System Robust to Corner Cases (with M2DGR-Plus)from ICRA2024

  • Calibration: GRIL-Calib: Targetless Ground Robot IMU-LiDAR Extrinsic Calibration Method using Ground Plane Motion Constraints from RA-L2023

  • Survey: Resilient and Distributed Multi-Robot Visual SLAM: Datasets, Experiments, and Lessons Learned from IROS2023

  • SLAM modules:

    • LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloud from RA-L2024

    • VoxelMap++: Mergeable Voxel Mapping Method for Online LiDAR(-inertial) Odometry from RA-L2023

  • SLAM systems:

    • Block-Map-Based Localization in Large-Scale Environment from ICRA2024

    • A High-Precision LiDAR-Inertial Odometry via Invariant Extended Kalman Filtering and Efficient Surfel Mapping from TIM2024

    • I2EKF-LO: A Dual-Iteration Extended Kalman Filter Based LiDAR Odometry from IROS2024

    • mVLINS: A Multilevel Visual-LiDAR-Inertial Navigation System with Completely Decoupled Odometry and Adaptive Environmental Mapping from TIV2024

    • Fast and Robust LiDAR-Inertial Odometry by Tightly-Coupled Iterated Kalman Smoother and Robocentric Voxels from TITS2024

    • LIVER: A Tightly Coupled LiDAR-Inertial-Visual State Estimator With High Robustness for Underground Environments from RA-L2024

    • LOG-LIO: A LiDAR-Inertial Odometry with Efficient Local Geometric Information Estimation from RA-L2023

    • Efficient 3D Deep LiDAR Odometry from T-PAMI2022

    • Swarm-SLAM: Sparse Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot Systems from RA-L2023

    • DAMS-LIO: A Degeneration-Aware and Modular Sensor-Fusion LiDAR-inertial Odometry from ICRA2023

• ⭐️2024/03/05: A quantity of cutting-edge SLAM systems have been tested on M2DGR by lovely users. Here are the configuration files for ORB-SLAM2, ORB-SLAM3, VINS-Mono,DM-VIO, A-LOAM, Lego-LOAM, LIO-SAM, LVI-SAM, LINS, FastLIO2,Fast-LIVO, Faster-LIO and hdl_graph_slam. Welcome to test! If you have more configuration files, please contact me and I will post it on this website ~

• 🚀 2024/02/22: New paper has been accepted by ICRA2024! The dataset is M2DGR-plus and Ground-Challenge. And the algorithm code is Ground-Fusion. The preprint paper is here.

• ⭐️2022/06/20: Thanks Jialin Liu (Fudan University) for his work to test LVI-SAM on M2DGR. Check out Here for a [modified LVI-SAM version] for M2DGR.

• ⭐️2022/02/18: We have upload a brand new SLAM dataset with GNSS, vision and IMU information. Here is our link SJTU-GVI. Different from M2DGR, new data is captured on a real car and it records GNSS raw measurements with a Ublox ZED-F9P device to facilitate GNSS-SLAM. Give us a star and folk the project if you like it.

• 📄 2022/02/01: The paper has been accepted by both RA-L and ICRA 2022. The paper is provided in Arxiv version and IEEE RA-L version.

[!NOTE] If you build your open-source project based on M2DGR or test a cutting-edge SLAM system on M2DGR, please write a issue to remind me of updating your contributions.

INTRODUCTION

ABSTRACT:

We introduce M2DGR: a novel large-scale dataset collected by a ground robot with a full sensor-suite including six fish-eye and one sky-pointing RGB cameras, an infrared camera, an event camera, a Visual-Inertial Sensor (VI-sensor), an inertial measurement unit (IMU), a LiDAR, a consumer-grade Global Navigation Satellite System (GNSS) receiver and a GNSS-IMU navigation system with real-time kinematic (RTK) signals. All those sensors were well-calibrated and synchronized, and their data were recorded simultaneously. The ground truth trajectories were obtained by the motion capture device, a laser 3D tracker, and an RTK receiver. The dataset comprises 36 sequences (about 1TB) captured in diverse scenarios including both indoor and outdoor environments. We evaluate state-of-the-art SLAM algorithms on M2DGR. Results show that existing solutions perform poorly in some scenarios. For the benefit of the research community, we make the dataset and tools public.

Keywords:Dataset, Multi-model, Multi-scenario,Ground Robot

MAIN CONTRIBUTIONS:

• We collected long-term challenging sequences for ground robots both indoors and outdoors with a complete sensor suite, which includes six surround-view fish-eye cameras, a sky-pointing fish-eye camera, a perspective color camera, an event camera, an infrared camera, a 32-beam LIDAR, two GNSS receivers, and two IMUs. To our knowledge, this is the first SLAM dataset focusing on ground robot navigation with such rich sensory information.
• We recorded trajectories in a few challenging scenarios like lifts, complete darkness, which can easily fail existing localization solutions. These situations are commonly faced in ground robot applications, while they are seldom discussed in previous datasets.
• We launched a comprehensive benchmark for ground robot navigation. On this benchmark, we evaluated existing state-of-the-art SLAM algorithms of various designs and analyzed their characteristics and defects individually.

VIDEO

For Chinese users, try

LICENSE

This work is licensed under MIT license. International License and is provided for academic purpose. If you are interested in our project for commercial purposes, please contact us on 1195391308@qq.com for further communication.

If you face any problem when using this dataset, feel free to propose an issue. And if you find our dataset helpful in your research, simply give this project a star. If you use M2DGR in an academic work, please cite:

@article{yin2021m2dgr,
  title={M2dgr: A multi-sensor and multi-scenario slam dataset for ground robots},
  author={Yin, Jie and Li, Ang and Li, Tao and Yu, Wenxian and Zou, Danping},
  journal={IEEE Robotics and Automation Letters},
  volume={7},
  number={2},
  pages={2266--2273},
  year={2021},
  publisher={IEEE}
}
@article{yin2024ground,
  title={Ground-Fusion: A Low-cost Ground SLAM System Robust to Corner Cases},
  author={Yin, Jie and Li, Ang and Xi, Wei and Yu, Wenxian and Zou, Danping},
  journal={arXiv preprint arXiv:2402.14308},
  year={2024}
}

SENSOR SETUP

Acquisition Platform

Physical drawings and schematics of the ground robot is given below. The unit of the figures is centimeter.

Sensor parameters

All the sensors and track devices and their most important parameters are listed as below:

• LIDAR Velodyne VLP-32C, 360 Horizontal Field of View (FOV),-30 to +10 vertical FOV,10Hz,Max Range 200 m,Range Resolution 3 cm, Horizontal Angular Resolution 0.2°.

• RGB Camera FLIR Pointgrey CM3-U3-13Y3C-CS,fish-eye lens,1280*1024,190 HFOV,190 V-FOV, 15 Hz

• GNSS Ublox M8T, GPS/BeiDou, 1Hz

• Infrared Camera,PLUG 617,640*512,90.2 H-FOV,70.6 V-FOV,25Hz;

• V-I Sensor,Realsense d435i,RGB/Depth 640*480,69H-FOV,42.5V-FOV,15Hz;IMU 6-axix, 200Hz

• Event Camera Inivation DVXplorer, 640*480,15Hz;

• IMU,Handsfree A9,9-axis,150Hz;

• GNSS-IMU Xsens Mti 680G. GNSS-RTK,localization precision 2cm,100Hz;IMU 9-axis,100 Hz;

• Laser Scanner Leica MS60, localization 1mm+1.5ppm

• Motion-capture System Vicon Vero 2.2, localization accuracy 1mm, 50 Hz;

The rostopics of our rosbag sequences are listed as follows:

• LIDAR: /velodyne_points

• RGB Camera: /camera/left/image_raw/compressed ,
  /camera/right/image_raw/compressed ,
  /camera/third/image_raw/compressed ,
  /camera/fourth/image_raw/compressed ,
  /camera/fifth/image_raw/compressed ,
  /camera/sixth/image_raw/compressed ,
  /camera/head/image_raw/compressed

• GNSS Ublox M8T:
  /ublox/aidalm ,
  /ublox/aideph ,
  /ublox/fix ,
  /ublox/fix_velocity ,
  /ublox/monhw ,
  /ublox/navclock ,
  /ublox/navpvt ,
  /ublox/navsat ,
  /ublox/navstatus ,
  /ublox/rxmraw

• Infrared Camera:/thermal_image_raw

• V-I Sensor:
  /camera/color/image_raw/compressed ,
  /camera/imu

• Event Camera:
  /dvs/events,
  /dvs_rendering/compressed

• IMU: /handsfree/imu

DATASET SEQUENCES

We make public ALL THE SEQUENCES with their GT now.

An overview of M2DGR is given in the table below:

Outdoors

Indoors

Alternative indoors and outdoors

CONFIGURATION FILES

For convenience of evaluation, we provide configuration files of some well-known SLAM systems as below:

A-LOAM, LeGO-LOAM, LINS, LIO-SAM, VINS-MONO, ORB-Pinhole, ORB-Fisheye, ORB-Thermal, and CUBMAPSLAM.

Furthermore, a quantity of cutting-edge SLAM systems have been tested on M2DGR by lovely users. Here are the configuration files for ORB-SLAM2, ORB-SLAM3, VINS-Mono,DM-VIO, A-LOAM, Lego-LOAM, LIO-SAM, LVI-SAM, LINS, FastLIO2, Fast-LIVO, Faster-LIO and hdl_graph_slam. Welcome to test! If you have more configuration files, please contact me and I will post it on this website ~

DEVELOPEMENT TOOLKIT

Extracting Images

• For rosbag users, first make image view

roscd image_view
rosmake image_view
sudo apt-get install mjpegtools

open a terminal,type roscore.And then open another,type

rosrun image_transport republish compressed in:=/camera/color/image_raw raw out:=/camera/color/image_raw respawn="true"

• For non-rosbag users,just take advantage of following script export_tum,export_euroc and get_csv to get data in formats of Tum or EuRoC.

Evaluation

We use open-source tool evo for evalutation. To install evo,type

pip install evo --upgrade --no-binary evo

To evaluate monocular visual SLAM,type

evo_ape tum street_07.txt your_result.txt -vaps

To evaluate LIDAR SLAM,type

evo_ape tum street_07.txt your_result.txt -vap

To test GNSS based methods,type

evo_ape tum street_07.txt your_result.txt -vp

Calibration

For camera intrinsics,visit Ocamcalib for omnidirectional model. visit Vins-Fusion for pinhole and MEI model. use Opencv for Kannala Brandt model

For IMU intrinsics,visit Imu_utils

For extrinsics between cameras and IMU,visit Kalibr For extrinsics between Lidar and IMU,visit Lidar_IMU_Calib For extrinsics between cameras and Lidar, visit Autoware

Getting RINEX files

For GNSS based methods like RTKLIB, we usually need to get data in the format of RINEX. To make use of GNSS raw measurements, we use Link toolkit.

ROS drivers for UVC cameras

We write a ROS driver for UVC cameras to record our thermal-infrared image. UVC ROS driver

Star History

ACKNOWLEGEMENT

This work is supported by NSFC(62073214). Authors from SJTU hereby express our appreciation.