UGV
NEGS-UGV
Synthetic multisensor UGV navigation and semantic perception
Gazebo Husky recordings on eight paths across an urban park, lake shore, dense forest and mountain hillside, with labelled LiDAR and stereo imagery and simulator pose truth.
Access links
Primary places to inspect, download, read about, or reproduce the dataset.
Quick facts
- Vehicle type
- UGV
- Environment
- Outdoor
- Data origin
- Simulation
- Sensor count
- 5
- Ground truth
- Available
- Calibration
- Parameters Only
- Annotations
- Available
Sensor overview
High-level sensor availability before the detailed sensor records below.
Ground truth
Reference scope, method, rate, coverage, and provenance.
| Scope | Method | Reference system | Count | Rate | Coverage |
Reference provenance
|
|---|---|---|---|---|---|---|
| 6DoF | Other | Gazebo simulator model states | Not reported | 1000 Hz | Full |
Reference provenance
Unknown
|
|
||||||
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
Table 2 supplies sensor-frame poses relative to base_link for the simulation; no physical calibration accuracy or raw calibration recording is asserted.
Known or intentional limitations
Reported constraints and characteristics to check before using the dataset.
Simulated sensors are noise-free; synthetic realism and real-world transfer require separate evaluation.
Stereo imagery is rendered statically from saved poses after navigation.
Ground and sky dominate many image labels; ground dominates most LiDAR labels except forest.
Different lighting conditions and dynamic elements are future work.
Cameras
simulated_stereo
- Model
- ZED-2
- Setup
- Stereo
- Count
- 1
- Effective cameras
- 2
- Modality
- Not Reported
- Resolution
- 1280 x 720
- Rate
- 25 Hz
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- 69 deg
- VFOV
- 42 deg
- Notes
- Simulated stereo system with 0.12 m baseline. Realistic and flat-color tagged left/right images are rendered from saved poses after navigation and inserted synchronously. Paper describes timestamp-named PNG files; current archive encoding and meaning of stereo-image totals need checking.
IMUs
Generic simulated IMU
- Model
- Not reported
- Count
- 1
- Accel / gyro
- Not reported
GNSS
Generic simulated GNSS receiver
- Model or name
- Generic simulated GNSS receiver
- Count
- 1
- Rate
- Not reported
- GNSS type
- NOT REPORTED
- Position output
- Available
- Velocity output
- Not reported
- Heading output
- Not reported
LiDAR
Ouster OS1-64
- Model or name
- Ouster OS1-64
- Count
- 1
- Dimensions
- 3
- Rate
- 10 Hz
- Channels
- Not reported
- Range
- Not reported
Radar
Not reported
Pitot tube
Not reported
Additional sensors
Other sensor
- Name
- Simulated wheel tachometers
- Count
- 4
- Rate
- 10 Hz
- Notes
- Four separate timestamped wheel angular-speed streams in rad/s; tachometers are not asserted to be physical encoders.
Annotations
Reported annotation availability and task support.
- Availability
- Available
- Format
- Flat-color pixel tags and LiDAR reflectivity class IDs
- Class count
- 15
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.
@article{sanchez2022negsugv,
author = {Sánchez, Manuel and Morales, Jesús and Martínez, Jorge L. and Fernández-Lozano, J. J. and García-Cerezo, Alfonso},
title = {Automatically Annotated Dataset of a Ground Mobile Robot in Natural Environments via Gazebo Simulations},
journal = {Sensors},
year = {2022},
volume = {22},
pages = {5599},
doi = {10.3390/s22155599}
}
Dataset corrections
Notice a specific issue after reviewing the page?
Report an inaccuracy