Cooperative Drone and Water Supply Truck Scheduling for Wildfire Fighting Using Deep Reinforcement Learning

Wildfires often spread rapidly and cause significant casualties and economic losses. Firefighting drones carrying water capsules provide an efficient way for wildfire extinguishing, but their operational capabilities are limited by their payloads. This weakness can be compensated by using ground veh...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin-Yuan Bai, Xin-Ya Chen, Hai-Feng Ling, Yu-Jun Zheng
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Drones
Subjects:
Online Access:https://www.mdpi.com/2504-446X/9/7/464
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246568599781376
author Lin-Yuan Bai
Xin-Ya Chen
Hai-Feng Ling
Yu-Jun Zheng
author_facet Lin-Yuan Bai
Xin-Ya Chen
Hai-Feng Ling
Yu-Jun Zheng
author_sort Lin-Yuan Bai
collection DOAJ
description Wildfires often spread rapidly and cause significant casualties and economic losses. Firefighting drones carrying water capsules provide an efficient way for wildfire extinguishing, but their operational capabilities are limited by their payloads. This weakness can be compensated by using ground vehicles to provide mobile water supply. To this end, this paper presents an optimization problem of scheduling multiple drones and water supply trucks for wildfire fighting, which allocates burning subareas to drones, routes drones to perform fire-extinguishing operations in burning subareas and reload water between every two consecutive operations, and routes trucks to provide timely water supply for drones. To solve the problem within the limited emergency response time, we propose a deep reinforcement learning method, which consists of an encoder for embedding the input instance features and a decoder for generating a solution by iteratively predicting the subarea selection decision through attention. Computational results on test instances constructed upon real-world wilderness areas demonstrate the performance advantages of the proposed method over a collection of heuristic and metaheuristic optimization methods.
format Article
id doaj-art-9172e722aeb4476e9c5bc1af67d8cfce
institution Kabale University
issn 2504-446X
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Drones
spelling doaj-art-9172e722aeb4476e9c5bc1af67d8cfce2025-08-20T03:58:27ZengMDPI AGDrones2504-446X2025-06-019746410.3390/drones9070464Cooperative Drone and Water Supply Truck Scheduling for Wildfire Fighting Using Deep Reinforcement LearningLin-Yuan Bai0Xin-Ya Chen1Hai-Feng Ling2Yu-Jun Zheng3College of Field Engineering, Army Engineering University of PLA, Nanjing 210007, ChinaSchool of Information Science and Technology, Hangzhou Normal University, Hangzhou 311121, ChinaCollege of Field Engineering, Army Engineering University of PLA, Nanjing 210007, ChinaCollege of Field Engineering, Army Engineering University of PLA, Nanjing 210007, ChinaWildfires often spread rapidly and cause significant casualties and economic losses. Firefighting drones carrying water capsules provide an efficient way for wildfire extinguishing, but their operational capabilities are limited by their payloads. This weakness can be compensated by using ground vehicles to provide mobile water supply. To this end, this paper presents an optimization problem of scheduling multiple drones and water supply trucks for wildfire fighting, which allocates burning subareas to drones, routes drones to perform fire-extinguishing operations in burning subareas and reload water between every two consecutive operations, and routes trucks to provide timely water supply for drones. To solve the problem within the limited emergency response time, we propose a deep reinforcement learning method, which consists of an encoder for embedding the input instance features and a decoder for generating a solution by iteratively predicting the subarea selection decision through attention. Computational results on test instances constructed upon real-world wilderness areas demonstrate the performance advantages of the proposed method over a collection of heuristic and metaheuristic optimization methods.https://www.mdpi.com/2504-446X/9/7/464firefightingdronesdrone–truck cooperationcooperative schedulingoptimizationdeep reinforcement learning (DRL)
spellingShingle Lin-Yuan Bai
Xin-Ya Chen
Hai-Feng Ling
Yu-Jun Zheng
Cooperative Drone and Water Supply Truck Scheduling for Wildfire Fighting Using Deep Reinforcement Learning
Drones
firefighting
drones
drone–truck cooperation
cooperative scheduling
optimization
deep reinforcement learning (DRL)
title Cooperative Drone and Water Supply Truck Scheduling for Wildfire Fighting Using Deep Reinforcement Learning
title_full Cooperative Drone and Water Supply Truck Scheduling for Wildfire Fighting Using Deep Reinforcement Learning
title_fullStr Cooperative Drone and Water Supply Truck Scheduling for Wildfire Fighting Using Deep Reinforcement Learning
title_full_unstemmed Cooperative Drone and Water Supply Truck Scheduling for Wildfire Fighting Using Deep Reinforcement Learning
title_short Cooperative Drone and Water Supply Truck Scheduling for Wildfire Fighting Using Deep Reinforcement Learning
title_sort cooperative drone and water supply truck scheduling for wildfire fighting using deep reinforcement learning
topic firefighting
drones
drone–truck cooperation
cooperative scheduling
optimization
deep reinforcement learning (DRL)
url https://www.mdpi.com/2504-446X/9/7/464
work_keys_str_mv AT linyuanbai cooperativedroneandwatersupplytruckschedulingforwildfirefightingusingdeepreinforcementlearning
AT xinyachen cooperativedroneandwatersupplytruckschedulingforwildfirefightingusingdeepreinforcementlearning
AT haifengling cooperativedroneandwatersupplytruckschedulingforwildfirefightingusingdeepreinforcementlearning
AT yujunzheng cooperativedroneandwatersupplytruckschedulingforwildfirefightingusingdeepreinforcementlearning