Automotive

Odyssey

Lidar-inertial odometry and localization

Automotive lidar and inertial dataset with 36 repeated-route sequences spanning ordinary roads, tunnels and indoor parking, with RLG-based RTK/INS reference poses.

Metadata: Complete Metadata needs review

Quick facts

Vehicle type
Automotive
Environment
Indoor, Outdoor
Data origin
Real-world
Sensor count
2
Ground truth
Available
Calibration
Not reported
Annotations
Not reported

Sensor overview

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

Ground truth

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

Ground-truth references for Odyssey
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 GNSS / INS iMAR reference RTK/INS · iPRENA-M-II Not reported 10 Hz Full 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
Validation includes 987 cross-run ICP registrations; urban cadastre comparison is limited to XY/yaw and gives 0.27 m combined map, ICP and reference uncertainty. The 0.067 percent drift result covers denied segments in two parking trajectories only. These are validation statistics rather than a universal 3D accuracy guarantee.
Reference notes
Separate RLG-based reference system generates 200 Hz fused pose and inertial output. Released reference WSV IMU and fused geodetic data remain reference products. KITTI-style poses are aligned to lidar times and relative to the first pose. Manual lidar ICP loop constraints refine loop-containing trajectories through GTSAM; others rely solely on INS. ParkingGarage1 and ParkingGarage2 contain bias-refinement discontinuities with timestamp intervals supplied in metadata.

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

Productive inertial outputs are prealigned to the lidar frame, with claimed extrinsic accuracy below 0.1 mm and 0.06 degrees. The reference frame is also pretransformed using mechanical design and hand-eye calibration. Both INS units are intrinsically calibrated using precision turntables.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Reference bias refinement can cause discontinuities in ParkingGarage1 and ParkingGarage2; interval timestamps are supplied in metadata.

Tunnel geometry and coherent moving traffic can defeat lidar and lidar-inertial registration.

Cameras

Not reported

IMUs

iNAT M300-TLE-LN1 productive-system IMU

Model
Not reported
Count
1
Accel / gyro
Not reported

GNSS

Not reported

LiDAR

Ouster OS1 rev.7

Model or name
Ouster OS1 rev.7
Count
1
Dimensions
3
Rate
10 Hz
Channels
128
Range
Not reported

Radar

Not reported

Pitot tube

Not reported

Additional sensors

Not reported

Annotations

Reported annotation availability and task support.

Availability
Not reported
Format
Not reported
Class count
Not reported
Semantic segmentation Not reported
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
Not reported

BibTeX

Not reported

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy