Public code and datasets for HDPlanner: Advancing Autonomous Deployments in Unknown Environments through Hierarchical Decision Networks, which has been accepted by IEEE Robotics and Automation Letters (RA-L).
We propose a hierarchical planning approach for robot exploration and navigation in unknown environments, where our decision networks decompose long-term objectives into short-term task assignment (beacon) and informative path planning (waypoint).
python == 3.8.8pytorch == 1.8.1ray == 1.2.0scikit-image == 0.21.0scikit-learn == 1.3.0scipy == 1.10.1matplotlib == 3.6.2tensorboard == 2.11.0
If you find our work helpful or enlightening, feel free to cite our paper:
@ARTICLE{10767278,
author={Liang, Jingsong and Cao, Yuhong and Ma, Yixiao and Zhao, Hanqi and Sartoretti, Guillaume},
journal={IEEE Robotics and Automation Letters},
title={HDPlanner: Advancing Autonomous Deployments in Unknown Environments Through Hierarchical Decision Networks},
year={2025},
volume={10},
number={1},
pages={256-263},
doi={10.1109/LRA.2024.3506281}
}
Jingsong Liang, Yuhong Cao, Yixiao Ma, Hanqi Zhao, Guillaume Sartoretti