|
|
论文:2012,Vol:30,Issue(3):340-344 |
|
|
引用本文： |
|
|
徐小野, 李爱军, 张丛丛, 姚宗信. 基于Q学习的变体无人机控制系统设计[J]. 西北工业大学 |
|
|
Xu Xiaoye, Li Aijun, Zhang Congcong, Yao Zongxin. Applying Q-Learning to Designing Feasible Morphing UAV Control System[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于Q学习的变体无人机控制系统设计 |
|
| 徐小野1, 李爱军1, 张丛丛1, 姚宗信2 |
|
1. 西北工业大学 自动化学院,陕西 西安 710072;
2. 中国航空工业集团公司 沈阳设计研究所,辽宁 沈阳 110000 |
| 摘要: |
| 针对变体无人机的控制问题,给出了Q学习控制方法。首先根据设计任务要求设计控制律控制变体无人机按给定航路完成飞行。同时根据飞行环境和飞行任务的变化,利用Q学习方法控制变体飞行器相应地改变外形(平直翼、小前掠翼、大前掠翼),使变体飞行器能始终保持最优飞行状态,以满足在变化很大的飞行环境里执行多种任务(如巡航、机动、盘旋、攻击等)的要求。仿真结果验证了该方法的正确性和有效性。 |
| 关键词:
变体无人机
Q学习
控制
|
|
| Applying Q-Learning to Designing Feasible Morphing UAV Control System |
|
| Xu Xiaoye1, Li Aijun1, Zhang Congcong1, Yao Zongxin2 |
|
| Department of Automatic Control,Northwestern Polytechnical University,Xi'an 710072,China |
| Abstract: |
| This paper develops a control methodology for morphing,which combines Q-Learning and PID Control.Sections 1 and 2 of the full paper explain our design mentioned in the title,which we believe is feasible or effectiveand whose core consists of: "The morphing control function, which uses Q-Learning, is integrated with the trajecto-ry tracking function,which uses PID Control. Optimality is addressed by cost functions representing optimal shapescorresponding to specified operating conditions,and an episodic‘reinforcement learning’simulation is developedto learn the optimal shape change policy. The methodology is demonstrated by a numerical example of a morphingair vehicle,which simultaneously tracks a specified trajectory and autonomously morphs over a set of shapes corre-sponding to flight conditions along the trajectory. "Simulation results, presented in Figs. 4 and 5, and their analysisshow preliminarily that this methodology is capable of learning the required shape and morphing into it and accu-rately tracking the reference trajectory,thus showing that our design is indeed feasible. |
| Key words:
control
design
efficiency
reinforcement learning
tracking(position)
UAV(unmanned aerial vehi-cles) ;flowcharting
morphing UAV
Q-learning
simulation
|
|
| 收稿日期: 2011-06-06
修回日期:
|
| DOI: |
| 基金项目: 航空科学基金(200907S3007)；国家国际科技合作专项基金(2011DFR81070)资助 |
| 通讯作者:
Email： |
| 作者简介: 徐小野(1986-),西北工业大学博士研究生,主要从事飞行器控制与仿真研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Northrop Grumman Corporation.Aircraft with Variable Forward Sweep Wing.USA: US5984231，1999
[2] 吴洪岩.基于强化学习的自主移动机器人导航研究.吉林: 东北师范大学，2009，11-13Wu Hongyan.The Research on Autonomous Mobile Robot Navigation Based on Reinforcement Learning.Jilin: Northeast NormalUniversity，2009: 11-13 (in Chinese)
[3] Amanda Lampton.Reinforcement Learning of a Morphing Airfoil-Policy and Discrete Learning Analysis.Journal of AerospaceComputing，Information，and Communication，2010: 241-260
[4] 刘文法，王 旭，张 乐，米 康.变前掠翼气动布局纵向性能研究.飞行力学，2008，26(4): 4-7Liu Wenfa，Wang Xu，Zhang Le，Mi Kang.Longitudinal Characteristics of the Aerodynamic Configuration with Variable For-ward-Swept Wing.Flight dynamics，2008，26(4): 4-7 (in Chinese)
[5] John Valasek.A Reinforcement Learning-Adaptive Control Architecture for Morphing.Journal of Aerospace Computing，Informa-tion，and Communication，2005: 174-195
[6] Jha A K，Kudva J N.Morphing Aircraft Concepts，Classifications，and Challenges.Industrial and Commercial Applications ofSmart Structures Technologies.Bellingham: SPIE，2004，213-224 |
|
|
|
|
|
|
|
