Mobile robot planning often involves finding the shortest path for a wheeled robot in the presence of obstacles. Planners often assume that the planning space is a 2-D Cartesian plane, with certain regions marked as off limits due to the presence of obstacles. When it comes to off-road vehicles, environments can also contain changes in elevation, turning this into a three-dimensional problem. Planning in higher-dimension spaces coincides with longer planning times, so an effective compromise can be to plan in a 2.5-D space using Digital Elevation Models (DEMs).
We encourage you to read and cite the following papers if you use any part of this repository for your research:
@inproceedings{DT-KO-2025,
author={Samak, Chinmay V. and Samak, Tanmay V. and Joglekar, Ajinkya S. and Vaidya, Umesh G. and Krovi, Venkat N.},
booktitle={2025 IEEE International Conference on Robotics and Automation (ICRA)},
title={Digital Twins Meet the Koopman Operator: Data-Driven Learning for Robust Autonomy},
year={2025},
volume={},
number={},
pages={9816-9822},
doi={10.1109/ICRA55743.2025.11128858}
}This work has been accepted at 2025 IEEE International Conference on Robotics & Automation (ICRA). The publication can be found on IEEE Xplore.