GEODE Dataset

Overview

Usage Steps

1. View the overview of the GEODE dataset, including sensor details, ROS topics and message definitions, and important considerations for localization evaluation.
2. Download the dataset from GEODE - Google Drive.
3. Adjust SLAM algorithms according to the provided parameters and compute errors after obtaining results.

Sensors

• Device α:
  • Velodyne VLP-16
  • Stereo HikRobot MV‑CS050‑10GC cameras
  • Xsens MTi‑30 IMU
• Device β:
  • Ouster OS1‑64
  • Stereo HikRobot MV‑CS050‑10GC cameras
  • Xsens MTi‑30 IMU
• Device γ:
  • Livox AVIA
  • Stereo HikRobot MV‑CS050‑10GC cameras
  • Xsens MTi‑30 IMU

Sensor Calibration

Calibration results are stored in three files: alpha.yaml, beta.yaml, gamma.yaml.

Localization Evaluation

An rmse.py script is provided to compute localization accuracy.

python3 rmse.py <Your traj> <GT traj> <time offset>

Dataset Details and Download

Click the GEODE dataset homepage for detailed information and to download the dataset.

Related Links

• Awesome-Algorithms-Against-Degeneracy
• SubT-MRS Dataset
• ENWIDE Dataset
• LiDAR Degeneracy Datasets
• WHU-Helmet Dataset
• CERBERUS
• CoSTAR
• CTU-CRAS-Norlab
• Explorer
• MARBLE COLORADAR DATASET

Publications

• Heterogeneous LiDAR Dataset for Benchmarking Robust Localization in Diverse Degenerate Scenarios Zhiqiang Chen, Yuhua Qi, Dapeng Feng, Xuebin Zhuang, Hongbo Chen, Xiangcheng Hu, Jin Wu, Kelin Peng, Peng Lu Under Review [Arxiv]