Reinforcement Learning Based Collaborative Path Planning Research for UAVs and Unmanned Vehicles

Xuanran Li, Longxin Yao, Mingzhe Li, Bo Zhang
Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, PMLR 278:595-603, 2025.

Abstract

This paper presents a reinforcement learning framework for multi-UAV and UGV coordinated path planning with charging constraints. We formulate the problem as a Markov Decision Process and develop a Transformer-based solution combining encoder-decoder architecture with policy gradients to optimize path synchronization and charging coordination. Experimental results demonstrate that our approach outperforms existing heuristic methods (GLS, TS) in terms of solution quality and generalization across different problem scales. The proposed method effectively minimizes mission completion time while handling energy constraints through intelligent charging point synchronization.

Cite this Paper

BibTeX
@InProceedings{pmlr-v278-li25j, title = {Reinforcement Learning Based Collaborative Path Planning Research for UAVs and Unmanned Vehicles}, author = {Li, Xuanran and Yao, Longxin and Li, Mingzhe and Zhang, Bo}, booktitle = {Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing}, pages = {595--603}, year = {2025}, editor = {Zeng, Nianyin and Pachori, Ram Bilas and Wang, Dongshu}, volume = {278}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v278/main/assets/li25j/li25j.pdf}, url = {https://proceedings.mlr.press/v278/li25j.html}, abstract = {This paper presents a reinforcement learning framework for multi-UAV and UGV coordinated path planning with charging constraints. We formulate the problem as a Markov Decision Process and develop a Transformer-based solution combining encoder-decoder architecture with policy gradients to optimize path synchronization and charging coordination. Experimental results demonstrate that our approach outperforms existing heuristic methods (GLS, TS) in terms of solution quality and generalization across different problem scales. The proposed method effectively minimizes mission completion time while handling energy constraints through intelligent charging point synchronization.} }
Endnote
%0 Conference Paper %T Reinforcement Learning Based Collaborative Path Planning Research for UAVs and Unmanned Vehicles %A Xuanran Li %A Longxin Yao %A Mingzhe Li %A Bo Zhang %B Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing %C Proceedings of Machine Learning Research %D 2025 %E Nianyin Zeng %E Ram Bilas Pachori %E Dongshu Wang %F pmlr-v278-li25j %I PMLR %P 595--603 %U https://proceedings.mlr.press/v278/li25j.html %V 278 %X This paper presents a reinforcement learning framework for multi-UAV and UGV coordinated path planning with charging constraints. We formulate the problem as a Markov Decision Process and develop a Transformer-based solution combining encoder-decoder architecture with policy gradients to optimize path synchronization and charging coordination. Experimental results demonstrate that our approach outperforms existing heuristic methods (GLS, TS) in terms of solution quality and generalization across different problem scales. The proposed method effectively minimizes mission completion time while handling energy constraints through intelligent charging point synchronization.
APA
Li, X., Yao, L., Li, M. & Zhang, B.. (2025). Reinforcement Learning Based Collaborative Path Planning Research for UAVs and Unmanned Vehicles. Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, in Proceedings of Machine Learning Research 278:595-603 Available from https://proceedings.mlr.press/v278/li25j.html.

Related Material