This package performs integrates fast distance field computations (gpu_voxels_ros) with whole-body motion planning using a trajectory optimisation approach. This package inlcudes an implementation of the Receding Horizon and Predictive Gaussian Process Motion Planner 2 (RHAP-GPMP2), as presented in Finean2022 listed below.
To build this package using catkin, please ensure that the environment variable GPU_VOXELS_INSTALL_DIR is set to your GPU-Voxels install directory.
If you use this work, please cite following publications:
@INPROCEEDINGS{Finean2022,
author={Finean, Mark Nicholas and Petrović, Luka and Merkt, Wolfgang and Marković, Ivan and Havoutis, Ioannis},
title={Motion Planning in Dynamic Environments Using Human Trajectory Prediction},
year={2022},
}
@inproceedings{Finean2021,
author = {Finean, Mark Nicholas and Merkt, Wolfgang and Havoutis, Ioannis},
booktitle = {2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
doi = {10.1109/IROS51168.2021.9636860},
eprint = {2103.03958},
isbn = {978-1-6654-1714-3},
month = {sep},
pages = {3710--3717},
publisher = {IEEE},
title = {{Simultaneous Scene Reconstruction and Whole-Body Motion Planning for Safe Operation in Dynamic Environments}},
year = {2021}
}
This repository is licensed under the BSD-3-Clause license.