航迹规划策略学习方法研究

doi:10.19678/j.issn.1000-3428.0054263

计算机工程 ›› 2020, Vol. 46 ›› Issue (5): 282-290,297. doi: 10.19678/j.issn.1000-3428.0054263

航迹规划策略学习方法研究

曹家敏¹, 付琦玮², 周丘实², 秦筱楲², 蔡超¹

1. 华中科技大学人工智能与自动化学院多谱信息处理技术国家级重点实验室, 武汉 430074;
2. 北京机电工程研究所, 北京 100074

收稿日期:2019-03-18 修回日期:2019-05-09 发布日期:2020-05-08
作者简介:曹家敏(1994-),女,硕士研究生,主研方向为航迹规划、计算机视觉;付琦玮,工程师、硕士;周丘实,硕士;秦筱楲,工程师、博士;蔡超,副教授、博士。
基金资助:
天津市智能遥感信息处理技术企业重点实验室开放基金（2016-ZW-KFJJ-01）。

Research on Learning Method for Flight Route Planning Strategy

CAO Jiamin¹, FU Qiwei², ZHOU Qiushi², QIN Xiaowei², CAI Chao¹

1. National Key Laboratory for Multi-spectral Information Processing Technologies, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China;
2. Beijing Research Institute of Mechanical and Electrical Engineering, Beijing 100074, China

Received:2019-03-18 Revised:2019-05-09 Published:2020-05-08

摘要/Abstract

摘要： 分析并研究航迹规划软件中的飞行器操作数据特征，提出一种基于XGBoost算法和K-prototypes算法的航迹规划策略学习方法。在样本采集与分类过程中，根据约束自身特性和规划人员操作特征，将约束分为飞行器环境约束和飞行器特性相关约束，分别采用XGBoost算法和K-prototypes算法进行策略学习，并对飞行器特性相关约束做进一步细分，实现复杂约束的针对性学习及样本分类管理。当航迹不满足约束时，需将已获得的规划策略反馈给规划人员使其得到策略引导。实验结果表明，该方法能准确选取航迹规划策略并给出策略引导信息，降低规划人员的工作强度，提升交互规划效率和规划软件的智能性。

关键词: 规划策略, 策略学习, 样本分类, XGBoost算法, K-prototypes算法

Abstract: This paper analyzes and studies the characteristics of aircraft operational data in flight rout planning software,proposes a learning method for route planning strategy based on the XGBoost algorithm and K-prototypes algorithm.During sample collection and classification,the features of constraints and operation of planners are analyzed,and constraints are accordingly divided into two categories:constraints of aircraft environment and constraints related to aircraft features.Relevant strategies are learnt by using the XGBoost algorithm and K-prototypes algorithm respectively.Constraints related to aircraft features are further subdivided for more specific learning of complex constraints and classified management of samples.If a flight route does not meet the constraints,the obtained planning strategies are returned to planners to provide strategic guidance.Experimental results show that the proposed method can effectively extract the flight route planning strategies and provide strategic guidance information,which reduces the workloads of planners,improving the efficiency of interactive planning and the intelligence of planning software.

Key words: planning strategy, strategy learning, sample classification, XGBoost algorithm, K-prototypes algorithm

中图分类号:

TP393

曹家敏, 付琦玮, 周丘实, 秦筱楲, 蔡超. 航迹规划策略学习方法研究[J]. 计算机工程, 2020, 46(5): 282-290,297.

CAO Jiamin, FU Qiwei, ZHOU Qiushi, QIN Xiaowei, CAI Chao. Research on Learning Method for Flight Route Planning Strategy[J]. Computer Engineering, 2020, 46(5): 282-290,297.

http://www.ecice06.com/CN/Y2020/V46/I5/282

图/表 21

20200513205206

20200513205210

20200513205214

20200513205220

20200513205227

20200513205231

20200513205235

20200513205253

20200513205258

20200513205310

20200513205315

20200513205321

20200513205326

20200513205331

20200513205336

20200513205341

20200513205347

20200513205352

20200513205358

20200513205403

20200513205407

参考文献

[1] DING Mingyue,ZHENG Changwen,ZHOU Chengping,et al.Unmanned aerial vehicle trajectory planning[M].Beijing:Electronic Industry Press,2009.(in Chinese)丁明跃,郑昌文,周成平,等.无人飞行器航迹规划[M].北京:电子工业出版社,2009.
[2] SZCZERBA R J,GALKOWSKI P,GLICKSTEIN I S,et al.Robust algorithm for real-time route planning[J].IEEE Transactions on Aerospace and Electronic System,2000,36(3):869-878.
[3] FU Qiwei,ZHANG Ke,QIN Xiaowei,et al.A clustering algorithm on the strategy extraction of operations in route planning software[J].Tactical Missile Technology,2018(2):60-65.(in Chinese)付绮玮,张克,秦筱楲,等.一种用于飞行器航迹规划操作规则提取的聚类算法[J].战术导弹技术,2018(2):60-65.
[4] ZHENG Changwen,YAN Ping,DING Mingyue,et al.Research status and trend of route planning for flying vehicles[J].Journal of Astronautics,2007,28(6):255-259.(in Chinese)郑昌文,严平,丁明跃,等.飞行器航迹规划研究现状与趋势[J].宇航学报,2007,28(6):255-259.
[5] XI Zheng.Study on mission planning of spaceflight applying artificial intelligence[J].Acta Aeronauticaet Astronautica Sinica,2007,28(4):791-795.(in Chinese)席政.人工智能在航天飞行任务规划中的应用研究[J].航空学报,2007,28(4):791-795.
[6] SUN Xixia,CAI Chao,SHEN Xubang.A new cloud model based human-machine cooperative path planning method[J].Joural of Intelligent and Robotic Systems,2015,79(1):3-19.
[7] WANG Guofang.Expert knowledge-assisted reinforcement learning research and its application in UAV path planning[D].Hangzhou:Zhejiang University,2017.(in Chinese)王国芳.专家知识辅助的强化学习研究及其在无人机路径规划中的应用[D].杭州:浙江大学,2017.
[8] HAO Chuanchuan,FANG Zhou,LI Ping.A 3-D route planning algorithm for unmanned aerial vehicle based on Q-learning[J].Journal of Shanghai Jiao Tong University,2012,46(12):1931-1935.(in Chinese)郝钏钏,方舟,李平.基于Q学习的无人机三维航迹规划算法[J].上海交通大学学报,2012,46(12):1931-1935.
[9] GILMORE J F,CZUCHRY A J.A neural network model for route planning constraint integration[C]//Proceedings of International Joint Conference on Neural Networks.Washington D.C.,USA:IEEE Press,1992:7-11.
[10] PASHKEVICH A,KAZHEUNIKAU M.Neural network approach to trajectory synthesis for robotic manipulators[J].Journal of Intelligent Manufacturing,2005,16:173-187.
[11] ANDRIY S,ERDAR K,TUFAN K,et al.Type-2 fuzzy logic controllers made even simpler:from design to deployment for UAVs[J].IEEE Transactions on Industrial Electronics,2017,65(6):5069-5077.
[12] LU Zhengding,FU Haidong.New approach for interpolative reasoning with multi-dimensonal sparse fuzzy rules[J].Journal of Chinese Computer Systems,2004,25(8):1468-1472.(in Chinese)[JP1]卢正鼎,符海东.一种新的多维稀疏规则模糊插值推理方法[J].小型微型计算机系统,2004,25(8):1468-1472.
[13] CHEN T,GUESTRIN C.XGBoost:a scalable tree boosting system[C]//Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2016:785-794.
[14] FRIEDMAN J H.Greedy function approximation:a gradient Boosting machine[J].Annals of Statistics,2001,29(5):1189-1232.
[15] MARCIN L,BARTOSZ T,MAGDALENA M.Application of XGBoost algorithm in fingerprinting localization task[C]//Proceedings of IFIP International Conference on Computer Information Systems and Industrial Management.Bialystok,Poland:[s.n.],2017:661-671.
[16] CHEN Wenbin,FU Kun,ZUO Jiawei,et al.Radar emitter classification for large data set based on weighted-XGBoost[J].IET Radar Sonar and Navigation,2017,11(8):1203-1207.
[17] LI Pin,ZHANG Jinsuo.A new hybrid method for China’s energy supply security forecasting based on ARIMA and XGBoost[J].Energies,2018,11(7):1687-1715.
[18] PHAM D,SUARE-ALVAREZ M,PROSTOV Y.Random search with k-prototypes algorithm for clustering mixed datasets[J].Proceeding of the Royal Society A:Mathematical,Physical and Engineering Sciences,2011,467(2132):2387-2403.
[19] GALAR M,FERNANDEZ A,BARRENECHEA E,et al.A review on ensembles for the class imbalance problem:Bagging-,Boosting-,and Hybrid-Based Approaches[J].IEEE Transactions on Systems,Man,and Cybernetics,Part C,2012,42(4):463-484.
[20] HUANG Zhexue.Extension to the k-means algorithm for clustering large data sets with categorical values[J].Data Mining and Knowledge Discovery,1998(2):283-304.
[21] HUANG Zhexue.Clustering large data sets with mixed numeric and categorical values[C]//Proceedings of the 1st Pacific-Asia Conference on Knowledge Discovery and Data Mining.Singapore:World Scientific,1997:1-5.
[22] BLASZCZYNSKI J,STEFANOWSKI J.Neighborhood sampling in Bagging for imbalanced data[J].Neurocomputing,2015,150:529-542.
[23] KAUFMAN L,ROUSSEEUW P.Finding groups in data:an introduction to cluster analysis[M].New York,USA:Wiley,2007.
[24] YE Feng.First-order logic and first-order theory[M].Beijing:China Social Science Press,1994.(in Chinese)叶峰.一阶逻辑与一阶理论[M].北京:中国社会科学出版社,1994.
[25] WANG Guojun.Axiomatic theory of truth degree for a class of first-order formulas and its application[J].SCIENTIA SINICA Informationis,2012,42(5):648-662.(in Chinese)王国俊.一类一阶逻辑公式中的公理化真度理论及其应用[J].中国科学:信息科学,2012,42(5):648-662.
[26] HUANG Zhuo,ZHANG Jian.Generating sat instances from first-order formulas[J].Joural of Software,2005,16(3):327-336.(in Chinese)黄拙,张健.由一阶逻辑公式得到命题逻辑可满足性问题实例[J].软件学报,2005,16(3):327-336.

选择文件类型/文献管理软件名称

选择包含的内容

航迹规划策略学习方法研究

Research on Learning Method for Flight Route Planning Strategy

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 21

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	常婷婷, 翟江涛, 戴跃伟. 一种基于Xgboost的Skype时间式隐信道检测方法[J]. 计算机工程, 2021, 47(7): 88-94.
[2]	邱月, 郑柏通, 蔡超. 多约束复杂环境下UAV航迹规划策略自学习方法[J]. 计算机工程, 2021, 47(5): 44-51.
[3]	杨晨, 梁意文, 谭成予, 周雯. 结合XGBoost的树突状细胞改进算法[J]. 计算机工程, 2019, 45(9): 194-197,203.
[4]	杨文潮,王际科,崔光海. 基于节点策略学习行为的社交网络合作促进机制[J]. 计算机工程, 2017, 43(11): 140-145.
[5]	杨扬, 孔令和, 李旭, 伍民友. 城市交通网络路径规划策略的性能分析[J]. 计算机工程, 2010, 36(21): 209-211.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

航迹规划策略学习方法研究

Research on Learning Method for Flight Route Planning Strategy

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 21

参考文献

相关文章 5

编辑推荐

Metrics

本文评价