Path Planning using Neural A* Search

Ryo Yonetani, Tatsunori Taniai, Mohammadamin Barekatain, Mai Nishimura, Asako Kanezaki
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12029-12039, 2021.

Abstract

We present Neural A*, a novel data-driven search method for path planning problems. Despite the recent increasing attention to data-driven path planning, machine learning approaches to search-based planning are still challenging due to the discrete nature of search algorithms. In this work, we reformulate a canonical A* search algorithm to be differentiable and couple it with a convolutional encoder to form an end-to-end trainable neural network planner. Neural A* solves a path planning problem by encoding a problem instance to a guidance map and then performing the differentiable A* search with the guidance map. By learning to match the search results with ground-truth paths provided by experts, Neural A* can produce a path consistent with the ground truth accurately and efficiently. Our extensive experiments confirmed that Neural A* outperformed state-of-the-art data-driven planners in terms of the search optimality and efficiency trade-off. Furthermore, Neural A* successfully predicted realistic human trajectories by directly performing search-based planning on natural image inputs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-yonetani21a, title = {Path Planning using Neural A* Search}, author = {Yonetani, Ryo and Taniai, Tatsunori and Barekatain, Mohammadamin and Nishimura, Mai and Kanezaki, Asako}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {12029--12039}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/yonetani21a/yonetani21a.pdf}, url = {https://proceedings.mlr.press/v139/yonetani21a.html}, abstract = {We present Neural A*, a novel data-driven search method for path planning problems. Despite the recent increasing attention to data-driven path planning, machine learning approaches to search-based planning are still challenging due to the discrete nature of search algorithms. In this work, we reformulate a canonical A* search algorithm to be differentiable and couple it with a convolutional encoder to form an end-to-end trainable neural network planner. Neural A* solves a path planning problem by encoding a problem instance to a guidance map and then performing the differentiable A* search with the guidance map. By learning to match the search results with ground-truth paths provided by experts, Neural A* can produce a path consistent with the ground truth accurately and efficiently. Our extensive experiments confirmed that Neural A* outperformed state-of-the-art data-driven planners in terms of the search optimality and efficiency trade-off. Furthermore, Neural A* successfully predicted realistic human trajectories by directly performing search-based planning on natural image inputs.} }
Endnote
%0 Conference Paper %T Path Planning using Neural A* Search %A Ryo Yonetani %A Tatsunori Taniai %A Mohammadamin Barekatain %A Mai Nishimura %A Asako Kanezaki %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-yonetani21a %I PMLR %P 12029--12039 %U https://proceedings.mlr.press/v139/yonetani21a.html %V 139 %X We present Neural A*, a novel data-driven search method for path planning problems. Despite the recent increasing attention to data-driven path planning, machine learning approaches to search-based planning are still challenging due to the discrete nature of search algorithms. In this work, we reformulate a canonical A* search algorithm to be differentiable and couple it with a convolutional encoder to form an end-to-end trainable neural network planner. Neural A* solves a path planning problem by encoding a problem instance to a guidance map and then performing the differentiable A* search with the guidance map. By learning to match the search results with ground-truth paths provided by experts, Neural A* can produce a path consistent with the ground truth accurately and efficiently. Our extensive experiments confirmed that Neural A* outperformed state-of-the-art data-driven planners in terms of the search optimality and efficiency trade-off. Furthermore, Neural A* successfully predicted realistic human trajectories by directly performing search-based planning on natural image inputs.
APA
Yonetani, R., Taniai, T., Barekatain, M., Nishimura, M. & Kanezaki, A.. (2021). Path Planning using Neural A* Search. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:12029-12039 Available from https://proceedings.mlr.press/v139/yonetani21a.html.

Related Material