List of Datasets

UGV

BotanicGarden

Navigation and sensor fusion in GNSS-denied natural environments

Botanic-garden stereo, dual-LiDAR, inertial and odometry collection with surveyed maps; a subset has direct downloads and further sequences are provided by request.

Metadata: Complete Metadata source documented Released 2023

Primary places to inspect, download, read about, or reproduce the dataset.

Quick facts

Vehicle type
UGV
Environment
Outdoor
Data origin
Real-world
Sensor count
9
Ground truth
Available
Calibration
Parameters Only
Annotations
Available

Sensor overview

High-level sensor availability before the detailed sensor records below.

Cameras

4 reported

IMUs

2 reported

GNSS

Not reported

LiDAR

2 reported

Radar

Not reported

Magnetometers

Not reported

Barometers

Not reported

UWB

Not reported

Ground truth

Reference scope, method, rate, coverage, and provenance.

Scope Method Reference system Count Rate Coverage Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
6DoF Other Survey-map localization with VIO and LiDAR registration · Leica RTC360 Not reported Not reported Unknown Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
Hybrid
Accuracy notes
32 stationary points: 0.6 cm normal / 2.3 cm dense vegetation; residual deskewing error remains.
Reference notes
Reference localization combines shared VIO/VLP16 observations with an independently surveyed Leica RTC360 map. Official GT_traj covers all thirty-three recorded paths; public raw bag membership is more limited.
Other Other Surveyed 3D map · Leica RTC360 Not reported Not reported Unknown Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
External
Reference notes
Summer/autumn maps from 515/400 scanner stations; 11 mm registration consistency is a map-level report.

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

Level
Parameters Only
Processed parameters
Available
Raw calibration data
Not reported
Calibration targets
Not reported

Parameters only

Processed calibration parameters are reported, but raw calibration data is not reported.

Notes

Maintained repository distributes calib/config parameters and calibration tools. Complete raw checkerboard/Aprilgrid/long static sessions are not established as downloadable products.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

The full collection comprises thirty-three runs and 17.1 km, while direct raw downloads list selected sample recordings and further sequences require contacting the authors. Current full-public recording/distance totals remain unknown.

ROS bags downsample imagery to 960x600 at 10 Hz; separate image archives retain 1920x1200 at 40 Hz. Hardware-trigger cadence is distinct from native inertial component sampling.

Leica survey-map consistency and stationary-point trajectory checks do not certify independent dynamic pose accuracy everywhere. Shared VIO/LiDAR observations contribute to the hybrid reference.

BMI088 acceleration requires the documented gravity-scale conversion. Raw encoders/magnetic data, full calibration sessions and achieved cross-stream alignment remain incompletely established; GNSS is not used.

Cameras

Camera 1

Model
DALSA M1930
Setup
Stereo
Count
1
Effective cameras
2
Modality
Grayscale
Resolution
1920 x 1200
Rate
40 Hz
Shutter
Global
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Full raw image ZIPs provide 1920x1200 at 40 Hz; easier-download bags contain 960x600 at 10 Hz. These are variants of the same camera system.

Camera 2

Model
DALSA C1930
Setup
Stereo
Count
1
Effective cameras
2
Modality
Rgb
Resolution
1920 x 1200
Rate
40 Hz
Shutter
Global
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Approximately 255 mm stereo baseline. Full raw image ZIPs provide 1920x1200 at 40 Hz; easier-download bags contain 960x600 at 10 Hz. These are variants of the same camera system.

IMUs

Livox Avia integrated IMU

Model
BMI088
Count
1
Accel / gyro
Not reported

Xsens industrial navigation IMU

Model
Xsens Mti-680G
Count
1
Accel / gyro
Not reported

GNSS

Not reported

LiDAR

Velodyne VLP16

Model or name
Velodyne VLP16
Count
1
Dimensions
3
Rate
10 Hz
Channels
16
Range
Not reported

Livox AVIA

Model or name
Livox AVIA
Count
1
Dimensions
3
Rate
10 Hz
Channels
Not reported
Range
Not reported

Radar

Not reported

Additional sensors

Odometry

Model
Scout V1.0 wheel dead reckoning
Name
Scout wheel dead reckoning
Count
1
Notes
The paper establishes processed wheel odometry with a 200 Hz reported rate and compensated CAN latency. Current topic list does not establish a separate raw encoder stream or fixed native encoder configuration.

Annotations

Reported annotation availability and task support.

Availability
Available
Format
LabelMe dense pixel masks; 1181 annotated images
Class count
27
Semantic segmentation Available
Instance segmentation Not reported
Object detection Not reported
Optical flow Not reported
Depth ground truth Not reported

Citation

Citation key and BibTeX kept at the end of the page for reference.

Citation key
liu2024botanicgarden

BibTeX

@ARTICLE{liu2024botanicgarden,
  author={Liu, Yuanzhi and Fu, Yujia and Qin, Minghui and Xu, Yufeng and Xu, Baoxin and Chen, Fengdong and Goossens, Bart and Sun, Poly Z.H. and Yu, Hongwei and Liu, Chun and Chen, Long and Tao, Wei and Zhao, Hui},
  journal={IEEE Robotics and Automation Letters}, 
  title={BotanicGarden: A High-Quality Dataset for Robot Navigation in Unstructured Natural Environments}, 
  year={2024},
  volume={9},
  number={3},
  pages={2798-2805},
  doi={10.1109/LRA.2024.3359548}}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy