UGV
LuSNAR
lunar rover navigation; semantic segmentation; 3D reconstruction
Simulated lunar rover stereo/LiDAR/inertial data with engine-generated pose, depth and terrain semantics.
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
- 4
- Ground truth
- Available
- Calibration
- Not reported
- 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 | AirSim engine pose | Not reported | Not reported | Full |
Reference provenance
Derived
|
|
||||||
| Other | Other | AirSim rendered left-camera depth | Not reported | 10 Hz | Full |
Reference provenance
Derived
|
|
||||||
Calibration and synchronization
Reported calibration level, reproducibility signals, and supporting notes.
- Level
- Not reported
- Processed parameters
- Not reported
- Raw calibration data
- Not reported
- Calibration targets
- Not reported
Calibration data
Calibration reproducibility details are not reported.
Notes
Simulation supplies configured intrinsics/extrinsics in rover NED and camera optical frames. Ideal camera geometry does not model real calibration error.
Known or intentional limitations
Reported constraints and characteristics to check before using the dataset.
This is an AirSim simulation of nine lunar scenes, not a real lunar sensor collection. Configured speed limits, noise and ideal camera geometry are not measured real-world performance.
The nine scene groups and per-frame samples have different denominators; no larger independent sequence count is inferred.
Rendered depth is distributed in PFM. The manuscript bit-depth wording is not treated as a verified storage dtype. Two-dimensional and three-dimensional semantic class sets differ.
Cameras
Camera 1
- Model
- Simulated AirSim stereo camera
- Setup
- Stereo
- Count
- 1
- Effective cameras
- 2
- Modality
- Rgb
- Resolution
- 1024 x 1024
- Rate
- 10 Hz
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- One simulated stereo system; 310 mm baseline and 80 by 80 degree field of view. Distortion and installation error are not modeled.
IMUs
Simulated AirSim IMU
- Model
- Simulated AirSim IMU
- Count
- 1
- Accel / gyro
- 100 / 100 Hz
GNSS
Not reported
LiDAR
Simulated spinning LiDAR
- Model or name
- Simulated spinning LiDAR
- Count
- 1
- Dimensions
- 3
- Rate
- 10 Hz
- Channels
- 128
- Range
- 30 m
Radar
Not reported
Additional sensors
Not reported
Annotations
Reported annotation availability and task support.
- Availability
- Available
- Format
- RGB and 2D semantic PNG, depth PFM, and 3D semantic points/IMU/poses. Five image classes and three point classes are distinct.
- Class count
- Not reported
Semantic segmentation
Available
Instance segmentation
Not reported
Object detection
Not reported
Optical flow
Not reported
Depth ground truth
Available
Citation
Citation key and BibTeX kept at the end of the page for reference.
@misc{liu2024lusnar,
author = {Jiayi Liu and Qianyu Zhang and Xue Wan and Shengyang Zhang and Yaolin Tian and Haodong Han and Yutao Zhao and Baichuan Liu and Zeyuan Zhao and Xubo Luo},
title = {LuSNAR: A Lunar Segmentation, Navigation and Reconstruction Dataset based on Multi-sensor for Autonomous Exploration},
year = {2024},
url = {https://arxiv.org/abs/2407.06512v3}
}Dataset corrections
Notice a specific issue after reviewing the page?
Report an inaccuracy