Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avoidance

Abstract Aiming at the problems of insufficient autonomous obstacle avoidance performance of UAVs in complex indoor environments, an improved Double DQN algorithm based on deep reinforcement learning is proposed. The algorithm enhances the perception and learning capabilities by optimizing the netwo...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruiqi Yu, Qingdang Li, Jiewei Ji, Tingting Wu, Jian Mao, Shun Liu, Zhen Sun
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-02356-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849388086112288768
author Ruiqi Yu
Qingdang Li
Jiewei Ji
Tingting Wu
Jian Mao
Shun Liu
Zhen Sun
author_facet Ruiqi Yu
Qingdang Li
Jiewei Ji
Tingting Wu
Jian Mao
Shun Liu
Zhen Sun
author_sort Ruiqi Yu
collection DOAJ
description Abstract Aiming at the problems of insufficient autonomous obstacle avoidance performance of UAVs in complex indoor environments, an improved Double DQN algorithm based on deep reinforcement learning is proposed. The algorithm enhances the perception and learning capabilities by optimizing the network model and employs a dynamic exploration strategy that encourages exploration in the early stage and reduces it later to accelerate convergence and improve efficiency. Simulation experiments in two scenarios of varying complexity, using an indoor simulation environment built with AirSim and UE4(Unreal Engine 4), show that in the simpler scenario, the average cumulative reward increased by 22.88%, the maximum reward increased by 101.56%, the average safe flight distance increased by 23.17%, and the maximum safe flight distance by 105.62%. In the more complex scenario, the average cumulative reward increased by 2.66%, the maximum reward increased by 88.77%, the average safe flight distance increased by 2.05%, and the maximum safe flight distance by 84.68%.
format Article
id doaj-art-66b2ee2b4f5c4aee86ec16e117e0fa32
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-66b2ee2b4f5c4aee86ec16e117e0fa322025-08-20T03:42:25ZengNature PortfolioScientific Reports2045-23222025-08-0115111710.1038/s41598-025-02356-6Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avoidanceRuiqi Yu0Qingdang Li1Jiewei Ji2Tingting Wu3Jian Mao4Shun Liu5Zhen Sun6College of Data Science, Qingdao University of Science and TechnologyCollege of Sino-German Science and Technology, Qingdao University of Science and TechnologyCollege of Data Science, Qingdao University of Science and TechnologyCollege of Data Science, Qingdao University of Science and TechnologyQingdao Central Hospital, University of Health and Rehabilitation SciencesCollege of Information Science and Technology, Qingdao University of Science and TechnologyCollege of Data Science, Qingdao University of Science and TechnologyAbstract Aiming at the problems of insufficient autonomous obstacle avoidance performance of UAVs in complex indoor environments, an improved Double DQN algorithm based on deep reinforcement learning is proposed. The algorithm enhances the perception and learning capabilities by optimizing the network model and employs a dynamic exploration strategy that encourages exploration in the early stage and reduces it later to accelerate convergence and improve efficiency. Simulation experiments in two scenarios of varying complexity, using an indoor simulation environment built with AirSim and UE4(Unreal Engine 4), show that in the simpler scenario, the average cumulative reward increased by 22.88%, the maximum reward increased by 101.56%, the average safe flight distance increased by 23.17%, and the maximum safe flight distance by 105.62%. In the more complex scenario, the average cumulative reward increased by 2.66%, the maximum reward increased by 88.77%, the average safe flight distance increased by 2.05%, and the maximum safe flight distance by 84.68%.https://doi.org/10.1038/s41598-025-02356-6UAVIndoor autonomous obstacle avoidanceDeep reinforcement learningDouble DQN algorithmDynamic exploration strategy
spellingShingle Ruiqi Yu
Qingdang Li
Jiewei Ji
Tingting Wu
Jian Mao
Shun Liu
Zhen Sun
Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avoidance
Scientific Reports
UAV
Indoor autonomous obstacle avoidance
Deep reinforcement learning
Double DQN algorithm
Dynamic exploration strategy
title Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avoidance
title_full Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avoidance
title_fullStr Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avoidance
title_full_unstemmed Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avoidance
title_short Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle avoidance
title_sort improved double dqn with deep reinforcement learning for uav indoor autonomous obstacle avoidance
topic UAV
Indoor autonomous obstacle avoidance
Deep reinforcement learning
Double DQN algorithm
Dynamic exploration strategy
url https://doi.org/10.1038/s41598-025-02356-6
work_keys_str_mv AT ruiqiyu improveddoubledqnwithdeepreinforcementlearningforuavindoorautonomousobstacleavoidance
AT qingdangli improveddoubledqnwithdeepreinforcementlearningforuavindoorautonomousobstacleavoidance
AT jieweiji improveddoubledqnwithdeepreinforcementlearningforuavindoorautonomousobstacleavoidance
AT tingtingwu improveddoubledqnwithdeepreinforcementlearningforuavindoorautonomousobstacleavoidance
AT jianmao improveddoubledqnwithdeepreinforcementlearningforuavindoorautonomousobstacleavoidance
AT shunliu improveddoubledqnwithdeepreinforcementlearningforuavindoorautonomousobstacleavoidance
AT zhensun improveddoubledqnwithdeepreinforcementlearningforuavindoorautonomousobstacleavoidance