Multi-robot Object SLAM with Distributed Variational Inference

[Paper]

Run the code

To run the algorithm on KITTI sequence 00. Change consensus_average value in the corresponding config file to switch between original MSCKF and our propose distributed MSCKF with consensus averaging.

python run.py --dataset kitti --data_id 00

To run it on simulation with 15 robots. Change consensus_average value in the corresponding config file to switch between original MSCKF and our propose distributed MSCKF with consensus averaging.

python run.py --dataset simulated --data_id nrobot_15

Evaluation

To evaluate the results on KITTI sequence 00

python evaluate_results.py --dataset kitti --data_id 00

To evaluate the results on simulation with 15 robots

python evaluate_results.py --dataset simulated --data_id nrobot_15

Citation

If you find this work useful, please consider to cite our paper:

@article{cao2024multi,
  title = {Multi-Robot Object {SLAM} Using Distributed Variational Inference},
  author = {Cao, Hanwen and Shreedharan, Sriram and Atanasov, Nikolay},
  journal = {IEEE Robotics and Automation Letters (RA-L)},
  year = {2024},
  volume = {9},
  number = {10},
  pages = {8722-8729},
  url = {https://arxiv.org/abs/2404.18331},
  doi = {https://doi.org/10.1109/LRA.2024.3451389}
}