An End-to-End Solution for Large-Scale Multi-UAV Mission Path Planning
With the increasing adoption of cooperative multi-UAV systems in applications such as cargo delivery and ground reconnaissance, the demand for scalable and efficient path planning methods has grown substantially. However, traditional heuristic algorithms are frequently trapped in local optima, requi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/6/418 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850156056073732096 |
|---|---|
| author | Jiazhan Gao Liruizhi Jia Minchi Kuang Heng Shi Jihong Zhu |
| author_facet | Jiazhan Gao Liruizhi Jia Minchi Kuang Heng Shi Jihong Zhu |
| author_sort | Jiazhan Gao |
| collection | DOAJ |
| description | With the increasing adoption of cooperative multi-UAV systems in applications such as cargo delivery and ground reconnaissance, the demand for scalable and efficient path planning methods has grown substantially. However, traditional heuristic algorithms are frequently trapped in local optima, require task-specific manual tuning, and exhibit limited generalization capabilities. Furthermore, their dependence on iterative optimization renders them unsuitable for large-scale real-time applications. To address these challenges, this paper introduces an end-to-end deep reinforcement learning framework that bypasses the reliance on handcrafted heuristic rules. The proposed method leverages an encoder–decoder architecture with multi-head attention (MHA), where the encoder generates embeddings for UAVs and task parameters, while the decoder dynamically selects actions based on contextual embeddings and enforces feasibility through a masking mechanism. The MHA module effectively models global spatial-task dependencies among nodes, enhancing solution quality. Additionally, we integrate a Multi-Start Greedy Rollout Baseline to evaluate diverse trajectories via parallelized greedy searches, thereby reducing policy gradient variance and improving training stability. Experiments demonstrated significant improvements in scalability, particularly in 100-node scenarios, where our method drastically reduced inference time compared to conventional methods, while maintaining a competitive path cost efficiency. A further validation on simulated mission environments and real-world geospatial data (sourced from Google Earth) underscored the robust generalization of the framework. This work advances large-scale UAV mission planning by offering a scalable, adaptive, and computationally efficient solution. |
| format | Article |
| id | doaj-art-ce9c39c7facb4e66b55656f0d4c09e78 |
| institution | OA Journals |
| issn | 2504-446X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-ce9c39c7facb4e66b55656f0d4c09e782025-08-20T02:24:42ZengMDPI AGDrones2504-446X2025-06-019641810.3390/drones9060418An End-to-End Solution for Large-Scale Multi-UAV Mission Path PlanningJiazhan Gao0Liruizhi Jia1Minchi Kuang2Heng Shi3Jihong Zhu4School of Computer Science and Technology, Xinjiang University, Urumqi 830017, ChinaSchool of Computer Science and Technology, Xinjiang University, Urumqi 830017, ChinaDepartment of Precision Instrument, Tsinghua University, Beijing 100084, ChinaDepartment of Precision Instrument, Tsinghua University, Beijing 100084, ChinaDepartment of Precision Instrument, Tsinghua University, Beijing 100084, ChinaWith the increasing adoption of cooperative multi-UAV systems in applications such as cargo delivery and ground reconnaissance, the demand for scalable and efficient path planning methods has grown substantially. However, traditional heuristic algorithms are frequently trapped in local optima, require task-specific manual tuning, and exhibit limited generalization capabilities. Furthermore, their dependence on iterative optimization renders them unsuitable for large-scale real-time applications. To address these challenges, this paper introduces an end-to-end deep reinforcement learning framework that bypasses the reliance on handcrafted heuristic rules. The proposed method leverages an encoder–decoder architecture with multi-head attention (MHA), where the encoder generates embeddings for UAVs and task parameters, while the decoder dynamically selects actions based on contextual embeddings and enforces feasibility through a masking mechanism. The MHA module effectively models global spatial-task dependencies among nodes, enhancing solution quality. Additionally, we integrate a Multi-Start Greedy Rollout Baseline to evaluate diverse trajectories via parallelized greedy searches, thereby reducing policy gradient variance and improving training stability. Experiments demonstrated significant improvements in scalability, particularly in 100-node scenarios, where our method drastically reduced inference time compared to conventional methods, while maintaining a competitive path cost efficiency. A further validation on simulated mission environments and real-world geospatial data (sourced from Google Earth) underscored the robust generalization of the framework. This work advances large-scale UAV mission planning by offering a scalable, adaptive, and computationally efficient solution.https://www.mdpi.com/2504-446X/9/6/418multi-UAV path planninglarge-scale path planningencoder–decoderrollout baselinemulti-head attention |
| spellingShingle | Jiazhan Gao Liruizhi Jia Minchi Kuang Heng Shi Jihong Zhu An End-to-End Solution for Large-Scale Multi-UAV Mission Path Planning Drones multi-UAV path planning large-scale path planning encoder–decoder rollout baseline multi-head attention |
| title | An End-to-End Solution for Large-Scale Multi-UAV Mission Path Planning |
| title_full | An End-to-End Solution for Large-Scale Multi-UAV Mission Path Planning |
| title_fullStr | An End-to-End Solution for Large-Scale Multi-UAV Mission Path Planning |
| title_full_unstemmed | An End-to-End Solution for Large-Scale Multi-UAV Mission Path Planning |
| title_short | An End-to-End Solution for Large-Scale Multi-UAV Mission Path Planning |
| title_sort | end to end solution for large scale multi uav mission path planning |
| topic | multi-UAV path planning large-scale path planning encoder–decoder rollout baseline multi-head attention |
| url | https://www.mdpi.com/2504-446X/9/6/418 |
| work_keys_str_mv | AT jiazhangao anendtoendsolutionforlargescalemultiuavmissionpathplanning AT liruizhijia anendtoendsolutionforlargescalemultiuavmissionpathplanning AT minchikuang anendtoendsolutionforlargescalemultiuavmissionpathplanning AT hengshi anendtoendsolutionforlargescalemultiuavmissionpathplanning AT jihongzhu anendtoendsolutionforlargescalemultiuavmissionpathplanning AT jiazhangao endtoendsolutionforlargescalemultiuavmissionpathplanning AT liruizhijia endtoendsolutionforlargescalemultiuavmissionpathplanning AT minchikuang endtoendsolutionforlargescalemultiuavmissionpathplanning AT hengshi endtoendsolutionforlargescalemultiuavmissionpathplanning AT jihongzhu endtoendsolutionforlargescalemultiuavmissionpathplanning |