ROAM: Riemannian Optimization for Active Mapping with Robot Teams

ROAM is a library for distributed multi-robot autonomous exploration using a stream of depth and semantic segmentation images as the input to build a semantically annotated OctoMap in real-time without any central mapping or planning node.

ROAM is implemented as two ROS packages, can be built on x86-64 and ARM-based processors:

• Distributed multi-robot semantic octree mapping of an environment (ROAM-Mapping)
• Distributed multi-robot collaborative safety and perception-aware exploration (ROAM-Planning)

Gazebo Demonstration

Please check https://github.com/ExistentialRobotics/ROAM-Example for a Gazebo demo of ROAM.

Citation

If you found this work useful, we would appreciate if you could cite our work:

• [1] A. Asgharivaskasi, F. Girke, N. Atanasov. Riemannian Optimization for Active Mapping with Robot Teams. arXiv:2404.18321.

@InProceedings{Asgharivaskasi-TRO24,
 title = {Riemannian Optimization for Active Mapping with Robot Teams},
 author = {Asgharivaskasi, Arash and Girke, Fritz and Atanasov, Nikolay},
 year = {2024},
 booktitle = {arxiv},
 pdf = {https://arxiv.org/pdf/2404.18321}
}

• [2] A. Asgharivaskasi, S. Koga, N. Atanasov. Active Mapping via Gradient Ascent Optimization of Shannon Mutual Information over Continuous SE(3) Trajectories. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.

@InProceedings{Asgharivaskasi-IROS22,
  author={Asgharivaskasi, Arash and Koga, Shumon and Atanasov, Nikolay},
  booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, 
  title={Active Mapping via Gradient Ascent Optimization of {S}hannon Mutual Information over Continuous {SE(3)} Trajectories}, 
  year={2022},
  pages={12994--13001}

Acknowledgments

We gratefully acknowledge support from NSF FRR CAREER 2045945 and ARL DCIST CRA W911NF-17-2-0181.

License

BSD License