List of Datasets

Other

Backpack2025

Degradation-robust lidar-inertial mapping

Eight released wearable dual-LiDAR/IMU mapping sequences span indoor and outdoor sites, with RTK-anchored, bundle-adjusted reference trajectories and maps.

Metadata: Complete Metadata source documented Released 2025

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

Supplementary

Not reported

Quick facts

Vehicle type
Other
Environment
Indoor, Outdoor
Data origin
Real-world
Sensor count
4
Ground truth
Available
Calibration
Parameters Only
Annotations
Not reported

Sensor overview

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

Cameras

Not reported

IMUs

1 reported

GNSS

1 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 Not reported 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.
Derived
Accuracy notes
Authors claim <3 cm, supported by few-centimeter aerial-map alignment residuals; not independent per-pose/indoor orientation validation.
Reference notes
Voxel SLAM/RTK anchoring followed by loop closure and offline lidar BA; RTK observations are omitted during final BA. GNSS lacks orientation. The maintained bag inventory includes RTK-GNSS alongside the LiDAR/IMU inputs; aerial maps provide separate checks rather than independently measured trajectory poses.
Other Other Not reported 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.
Derived
Reference notes
Reference map from the same RTK-anchored lidar bundle-adjustment pipeline. DJI Mavic 3/RTK and DJI Terra photogrammetric maps validate spatial alignment; their raw images are not established released streams. The maintained bag inventory includes RTK-GNSS alongside the LiDAR/IMU inputs; aerial maps provide separate checks rather than independently measured trajectory poses.

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

Documented calib.yaml includes LiDAR/IMU alignment and time offset, inter-LiDAR transform and GNSS lever arm; raw calibration recordings are not established.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

The maintained release now provides eight Baidu Netdisk sequences; the selected July manuscript only promised future access. Access can depend on the hosting provider.

Current archive-table totals are 11,067.9 m, 12,036.2 s and 654 GB. Historical manuscript site associations/rounding differ; these totals describe the maintained eight-row release.

Dual-LiDAR/IMU mapping and RTK anchoring produce the reference. GNSS is also listed in the released bags; the trajectory therefore reuses normal inputs. Aerial map checks do not certify every indoor pose or orientation.

Published IMU output is 400 Hz, while native component sampling and complete raw calibration recordings remain unknown.

Cameras

Not reported

IMUs

Backpack IMU

Model
Xsens MTi-630
Count
1
Accel / gyro
Not reported

GNSS

GNSS 1

Model or name
Not reported
Count
1
Rate
1 Hz
GNSS type
RTK
Position output
Available
Velocity output
Not reported
Heading output
Not reported

LiDAR

PandarXT-32

Model or name
PandarXT-32
Count
2
Dimensions
3
Rate
10 Hz
Channels
Not reported
Range
Not reported

Radar

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
jin2025backpackv1

BibTeX

@misc{jin2025backpackv1,
  title={Large-Scale LiDAR-Inertial Dataset for Degradation-Robust High-Precision Mapping},
  author={Jin, Xiaofeng and Bu, Ningbo and Ge, Jianfei and Wang, Shijie and Xiao, Jiangjian and Matteucci, Matteo},
  year={2025},
  eprint={2507.20516},
  archivePrefix={arXiv},
  note={Selected version 1, dated 28 July 2025}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy