EnvoDat dataset

Official development and benchmarking kit for EnvoDat. To replicate all the results in the official EnvoDat project website, we strongly recommend using this repository to run our pre-trained models, train on custom datasets, run inferences on the models and perform benchmark evaluation of the SoTA SLAM algorithms.

Getting Started

To learn more about using EnvoDat for training, benchmarking, and evaluating supervised learning models and perception algorithms, kindly refer to GET_STARTED.md.

Summary Video

License

This work is licensed under a Creative Commons Attribution International 4.0 License.

Paper Citation

If you use this work in your research, please cite our paper and dataset using the following BibTeX entry:

@misc{nwankwo2024envodatlargescalemultisensorydataset,
      title={EnvoDat: A Large-Scale Multisensory Dataset for Robotic Spatial Awareness and Semantic Reasoning in Heterogeneous Environments}, 
      author={Linus Nwankwo and Bjoern Ellensohn and Vedant Dave and Peter Hofer and Jan Forstner and Marlene Villneuve and Robert Galler and Elmar Rueckert},
      year={2024},
      eprint={2410.22200},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2410.22200}, 
}

Dataset Citation

@software{envodat,
    author = {Linus Nwankwo and Bjoern Ellensohn and Vedant Dave and Peter Hofer and Jan Forstner and Marlene Villneuve and Robert Galler and Elmar Rueckert},
    title = {EnvoDat: A Large-Scale Multisensory Dataset for Robotic Spatial Awareness and Semantic Reasoning in Heterogeneous Environments},
    note = {Project Website: \url{https://linusnep.github.io/EnvoDat/}},
    eprint={2410.22200},
    archivePrefix={arXiv},
    url={https://linusnep.github.io/EnvoDat/}
}

Acknowledgement

This project has received funding from the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - No #430054590 (TRAIN).