Deep Reinforcement Learning for the Visual Servoing Control of UAVs with FOV Constraint

Author:

Fu Gui12ORCID,Chu Hongyu1,Liu Liwen2,Fang Linyi2,Zhu Xinyu2

Affiliation:

1. School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, China

2. Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China, Guanghan 618307, China

Abstract

Visual servoing is a control method that utilizes image feedback to control robot motion, and it has been widely applied in unmanned aerial vehicle (UAV) motion control. However, due to field-of-view (FOV) constraints, visual servoing still faces challenges, such as easy target loss and low control efficiency. To address these issues, visual servoing control for UAVs based on the deep reinforcement learning (DRL) method is proposed, which dynamically adjusts the servo gain in real time to avoid target loss and improve control efficiency. Firstly, a Markov model of visual servoing control for a UAV under field-of-view constraints is established, which consists ofquintuplet and considers the improvement of the control efficiency. Secondly, an improved deep Q-network (DQN) algorithm with a target network and experience replay is designed to solve the Markov model. In addition, two independent agents are designed to adjust the linear and angular velocity servo gains in order to enhance the control performance, respectively. In the simulation environment, the effectiveness of the proposed method was verified using a monocular camera.

Funder

National Natural Science Foundation of China

Fund project for basic scientific research expenses of central universities

Independent research project of the Key Laboratory of Flight Techniques and Flight Safety

Publisher

MDPI AG

Subject

Artificial Intelligence,Computer Science Applications,Aerospace Engineering,Information Systems,Control and Systems Engineering

Reference29 articles.

1. UAV assistance paradigm: State-of-the-art in applications and challenges;Alzahrani;J. Netw. Comput. Appl.,2020

2. Multirotor Aerial Vehicles: Modeling, Estimation, and Control of Quadrotor;Mahony;IEEE Robot. Autom. Mag.,2012

3. An intelligent cooperative mission planning scheme of UAV swarm in uncertain dynamic environment;Zhen;Aerosp. Sci. Technol.,2020

4. Reinforcement learning based two-level control framework of UAV swarm for cooperative persistent surveillance in an unknown urban area;Liu;Aerosp. Sci. Technol.,2020

5. An online route planning method for multi-rotor drone in urban environments;Wu;Control. Decis.,2021

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3