# RTK-SLAM Dataset: Handheld LiDAR-Visual-Inertial Recordings with RTK GNSS for Absolute Accuracy in GNSS-Degraded Environments (University of Stuttgart)

## Facts

- Provider: Institute for Photogrammetry and Geoinformatics, University of Stuttgart (Zhang, Ress, Skuddis, Soergel, Haala)
- License: CC-BY-4.0 (https://huggingface.co/datasets/Willyzw/rtk-slam-dataset)
- Size: 18 files
- Stored at: Hugging Face, https://huggingface.co/datasets/Willyzw/rtk-slam-dataset
- Access: public, readable without an account
- Category: Robotics
- Source: https://huggingface.co/papers/2604.07151
- Page: https://scigantic.com/archive/d1bbac85-8c2d-5f09-aa77-e607266085d9
- Keywords: Robotics, LiDAR, benchmark, Hugging Face

## About

A benchmark for the absolute (georeferenced) accuracy of SLAM and sensor fusion when satellite positioning is partly blocked, from the Institute for Photogrammetry and Geoinformatics at the University of Stuttgart. A handheld rig carried a Livox MID360 LiDAR with built-in IMU (10 Hz scans, 200 Hz inertial), a 2 MP global-shutter camera at 20 Hz and a Unicore UM980 GNSS receiver at 10 Hz with real-time kinematic (RTK) corrections from the German SAPOS service. Four sequences were walked: two in Stuttgart's Stadtgarten park (1.04 km and 0.46 km, with tree cover, building shadowing and a 30 m underpass) and two at the IntCDC construction hall (0.48 km and 0.39 km, with a GNSS-denied indoor hall of more than 400 s), with 16 to 36 surveyed checkpoints per sequence and RTK fix rates of 23 to 54 percent. Every sequence is provided as a ROS 1 bag, a ROS 2 db3 bag and an extended EuRoC-format zip compatible with OKVIS2-X; camera timestamps are already corrected for the trigger delay. About 182 GB (measured 2026-11-21). Released under CC BY 4.0; cite Zhang et al., ISPRS Annals 2025.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="Willyzw/rtk-slam-dataset", filename="euroc/construction_seq1_euroc.zip", repo_type="dataset")
print(path)
```

## Data structure

Example file: `euroc/construction_seq1_euroc.zip`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/d1bbac85-8c2d-5f09-aa77-e607266085d9
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/d1bbac85-8c2d-5f09-aa77-e607266085d9
- Over MCP: `get_schema_card` with id `d1bbac85-8c2d-5f09-aa77-e607266085d9` at https://api.scigantic.com/mcp

## Related topics

- [Benchmark datasets](https://scigantic.com/topics/benchmark)
- [LiDAR datasets](https://scigantic.com/topics/lidar)
- [Robotics datasets](https://scigantic.com/topics/robotics)
