Path Planning for Agricultural UAVs Based on Deep Reinforcement Learning and Energy Consumption Constraints

Traditional pesticide application methods pose systemic threats to sustainable agriculture due to inefficient spraying practices and ecological contamination. Although agricultural drones demonstrate potential to address these challenges, they face critical limitations in energy-constrained complete...

Full description

Saved in:
Bibliographic Details
Main Authors: Haitao Fu, Zheng Li, Weijian Zhang, Yuxuan Feng, Li Zhu, Yunze Long, Jian Li
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/9/943
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850155853385039872
author Haitao Fu
Zheng Li
Weijian Zhang
Yuxuan Feng
Li Zhu
Yunze Long
Jian Li
author_facet Haitao Fu
Zheng Li
Weijian Zhang
Yuxuan Feng
Li Zhu
Yunze Long
Jian Li
author_sort Haitao Fu
collection DOAJ
description Traditional pesticide application methods pose systemic threats to sustainable agriculture due to inefficient spraying practices and ecological contamination. Although agricultural drones demonstrate potential to address these challenges, they face critical limitations in energy-constrained complete coverage path planning for field operations. This study proposes a novel BiLG-D3QN algorithm by integrating deep reinforcement learning with Bi-LSTM and Bi-GRU architectures, specifically designed to optimize segmented coverage path planning under payload-dependent energy consumption constraints. The methodology encompasses four components: payload-energy consumption modeling, soybean cultivation area identification using Google Earth Engine-derived spatial distribution data, raster map construction, and enhanced segmented coverage path planning implementation. Through simulation experiments, the BiLG-D3QN algorithm demonstrated superior coverage efficiency, outperforming DDQN by 13.45%, D3QN by 12.27%, Dueling DQN by 14.62%, A-Star by 15.59%, and PPO by 22.15%. Additionally, the algorithm achieved an average redundancy rate of only 2.45%, which is significantly lower than that of DDQN (18.89%), D3QN (17.59%), Dueling DQN (17.59%), A-Star (21.54%), and PPO (25.12%). These results highlight the notable advantages of the BiLG-D3QN algorithm in addressing the challenges of pesticide spraying tasks in agricultural UAV applications.
format Article
id doaj-art-d7eae85fe98a438093d5d0f8dd574c74
institution OA Journals
issn 2077-0472
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-d7eae85fe98a438093d5d0f8dd574c742025-08-20T02:24:46ZengMDPI AGAgriculture2077-04722025-04-0115994310.3390/agriculture15090943Path Planning for Agricultural UAVs Based on Deep Reinforcement Learning and Energy Consumption ConstraintsHaitao Fu0Zheng Li1Weijian Zhang2Yuxuan Feng3Li Zhu4Yunze Long5Jian Li6College of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaTraditional pesticide application methods pose systemic threats to sustainable agriculture due to inefficient spraying practices and ecological contamination. Although agricultural drones demonstrate potential to address these challenges, they face critical limitations in energy-constrained complete coverage path planning for field operations. This study proposes a novel BiLG-D3QN algorithm by integrating deep reinforcement learning with Bi-LSTM and Bi-GRU architectures, specifically designed to optimize segmented coverage path planning under payload-dependent energy consumption constraints. The methodology encompasses four components: payload-energy consumption modeling, soybean cultivation area identification using Google Earth Engine-derived spatial distribution data, raster map construction, and enhanced segmented coverage path planning implementation. Through simulation experiments, the BiLG-D3QN algorithm demonstrated superior coverage efficiency, outperforming DDQN by 13.45%, D3QN by 12.27%, Dueling DQN by 14.62%, A-Star by 15.59%, and PPO by 22.15%. Additionally, the algorithm achieved an average redundancy rate of only 2.45%, which is significantly lower than that of DDQN (18.89%), D3QN (17.59%), Dueling DQN (17.59%), A-Star (21.54%), and PPO (25.12%). These results highlight the notable advantages of the BiLG-D3QN algorithm in addressing the challenges of pesticide spraying tasks in agricultural UAV applications.https://www.mdpi.com/2077-0472/15/9/943precision agriculturedeep reinforcement learning path planning Bi-RNN
spellingShingle Haitao Fu
Zheng Li
Weijian Zhang
Yuxuan Feng
Li Zhu
Yunze Long
Jian Li
Path Planning for Agricultural UAVs Based on Deep Reinforcement Learning and Energy Consumption Constraints
Agriculture
precision agriculture
deep reinforcement learning path planning Bi-RNN
title Path Planning for Agricultural UAVs Based on Deep Reinforcement Learning and Energy Consumption Constraints
title_full Path Planning for Agricultural UAVs Based on Deep Reinforcement Learning and Energy Consumption Constraints
title_fullStr Path Planning for Agricultural UAVs Based on Deep Reinforcement Learning and Energy Consumption Constraints
title_full_unstemmed Path Planning for Agricultural UAVs Based on Deep Reinforcement Learning and Energy Consumption Constraints
title_short Path Planning for Agricultural UAVs Based on Deep Reinforcement Learning and Energy Consumption Constraints
title_sort path planning for agricultural uavs based on deep reinforcement learning and energy consumption constraints
topic precision agriculture
deep reinforcement learning path planning Bi-RNN
url https://www.mdpi.com/2077-0472/15/9/943
work_keys_str_mv AT haitaofu pathplanningforagriculturaluavsbasedondeepreinforcementlearningandenergyconsumptionconstraints
AT zhengli pathplanningforagriculturaluavsbasedondeepreinforcementlearningandenergyconsumptionconstraints
AT weijianzhang pathplanningforagriculturaluavsbasedondeepreinforcementlearningandenergyconsumptionconstraints
AT yuxuanfeng pathplanningforagriculturaluavsbasedondeepreinforcementlearningandenergyconsumptionconstraints
AT lizhu pathplanningforagriculturaluavsbasedondeepreinforcementlearningandenergyconsumptionconstraints
AT yunzelong pathplanningforagriculturaluavsbasedondeepreinforcementlearningandenergyconsumptionconstraints
AT jianli pathplanningforagriculturaluavsbasedondeepreinforcementlearningandenergyconsumptionconstraints