Description

We take advantage of our Avenger 8x8 driving platform to develop a challenging off-road dataset in mountainous and forested scenarios. We equiped our platform with two industrial camera, two Velodyne laser scanner and a GPS localization system. The dataset is comprised of 5 sequences captured while driving in the mountains around Changchun. Each sequence contains a set of point cloud data, odometry data, and imu data which can be used in LiDAR-based SLAM task. In the future, we will gradually release other data, such as images and annotations for tasks such as environmental perception, semantic segmentation. We will also release the data in different seasons. Coming soon.

 

Acknowledgement

When using this dataset in your research, we will be happy if you cite our website. We would appreciate if you can send an email to let us know when you use this dataset or when the dataset appears in a publicaton. Please also feel free to contact us If you encounter difficulties in using the dataset or have any suggestions regarding our dataset.

 

Copyright

All datasets on this page are copyright by us and published under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License. This means that you must attribute the work in the manner specified by the authors, you may not use this work for commercial purposes and if you alter, transform, or build upon this work, you may distribute the resulting work only under the same license.

Tool name
 
Description
 
Auth
 
Date
 
Description
 
JORD ROS Yu Chen 2022-11-01 This tool can be used to convert JORD datasets to ros bags, or play them directly like ros bag.

 

This page provides additional information about the recording platform and sensor setup we have used to record this dataset.

 

Computer

We used industrial computer when collecting data, and its main configuration is as follows

# Version
OS Ubuntu 20.04 LTS
CPU Intel i7-6770HQ
Memory 8G
Disk Samsung nvme 2T SSD

Sensors

Our recording platform is equipped with the following sensors

SensorName count config
Velodyne VLP-16 2 Strongest Return Mode
USB Camera 2 1280x720, 30fps, JPEG
NovAtel npos220s 1 10Hz #INSPVAXA sentence, 125Hz #RAWIMUA sentence
Sequence
 
Details
 
Lidar Frames
 
Trace Length
 
Package Size
 
Duration
 
JORD-01 3508 frames 374.4 meters 4 GB 377.9 seconds
JORD-02 8216 frames 872.3 meters 9 GB 869.2 seconds
JORD-03 5444 frames 654.2 meters 6 GB 576.4 seconds
JORD-04 5144 frames 618.3 meters 5 GB 541.7 seconds
JORD-05 5157 frames 719.3 meters 5 GB 550.1 seconds

第四届国际创新创业博览会

        2019年12月20日在北京国家会议中心,团队携项目“人工智能无人地面车平台”,代表吉林省总工会赴京参展,该设备特色鲜明、独具魅力,得到参观领导与嘉宾的高度关注。