perceptual-kiss-slam 0.0.3

KISS-SLAM: A Simple, Robust, and Accurate 3D LiDAR SLAM System With Enhanced Generalization Capabilities

KISS-SLAM

Install   •   Paper   •   Contact Us

KISS-SLAM is a simple, robust, and accurate 3D LiDAR SLAM system that just works.

---

Install

pip install kiss-slam

Running the system

Next, follow the instructions on how to run the system by typing:

kiss_slam_pipeline --help

This should print the following help message:

Config

You can generate a default config.yaml by typing:

kiss_slam_dump_config

which will generate a kiss_slam.yaml file. Now, you can modify the parameters and pass the file to the --config option when running the kiss_slam_pipeline.

Suggestion for indoor applications:

1. Reduce the odometry.preprocessing.max_range to 50.0, this will automatically reduce the voxel_size to 0.5.
2. Reduce the local_mapper.splitting_distance to a suitable distance based on the scale of the indoor environment.

Install Python API (developer mode)

For development purposes:

sudo apt install git python3-pip libeigen3-dev libsuitesparse-dev
python3 -m pip install --upgrade pip
git clone https://github.com/PRBonn/kiss-slam.git
cd kiss-slam
make editable

Paper Results

As we decided to continue developing KISS-SLAM beyond the scope of the IROS paper, we created a git tag so that researchers can consistently reproduce the results presented in the publication. To checkout at this tag, you can run the following:

git checkout IROS25

Our development aims to surpass the performance of KISS-SLAM beyond the original results presented in the paper.

Citation

If you use this library for any academic work, please cite our original paper:

@article{kiss2025arxiv,
  author   = {T. Guadagnino and B. Mersch and S. Gupta and I. Vizzo and G. Grisetti and C. Stachniss},
  title    = {{KISS-SLAM: A Simple, Robust, and Accurate 3D LiDAR SLAM System With Enhanced Generalization Capabilities}},
  journal  = {arXiv preprint},
  year     = 2025,
  volume   = {arXiv:2503.12660},
  url      = {https://arxiv.org/pdf/2503.12660},
}

Acknowledgements

This project builds on top of KISS-ICP, MapClosures, and g2o.

Contributing

We envision KISS-SLAM as a community-driven project. We love to see how the project is growing, thanks to the contributions from the community. We would love to see your face in the list below; open a Pull Request!

Contact Us

For questions or feedback:

• GitHub Issues: https://github.com/PRBonn/kiss-slam/issues