基于径向基函数神经网络辅助容积卡尔曼滤波的多自主水下航行器协同定位方法

doi:10.3969/j.issn.1000-1093.2019.10.018

摘要/Abstract

摘要： 在多自主水下航行器(AUV)协同定位系统中，针对协同定位性能受到系统内部和外部等多种因素制约的问题，提出一种基于径向基函数(RBF)神经网络辅助容积卡尔曼滤波(CKF)的多AUV协同定位方法。当基准参考位置可用时，通过非线性CKF得到滤波新息、预测误差和滤波增益作为RBF神经网络输入层的输入，滤波误差值作为输出对RBF神经网络进行训练；当基准信号中断时，利用训练好的RBF神经网络，对CKF的滤波状态估计值进行补偿，进而得到新的估计状态。利用湖试数据，模拟多AUV协同定位系统输入存在误差情况下的协同定位实验。实验结果表明，所提方法与无RBF辅助的CKF方法相比，平均定位误差减小70%，具有更好的准确性和稳定性。

关键词: 自主水下航行器, 协同定位, 径向基函数, 容积卡尔曼滤波

Abstract: For cooperative localization of autonomous underwater vehicles (AUVs), a multi-AUV cooperative localization method based on radial basis function (RBF) neural network-assisted cubature Kalman filter (CKF) is proposed to solve the problem that the cooperative localization performance is restricted by various factors, such as internal and external factors of cooperative localization system. When a basic reference position is available, the filtering innovation, prediction error and filtering gain, which are extracted from the nonlinear filtering CKF, are used as the inputs of the input layer of RBF neural network, and the filtering error value is used as an output to train the RBF neural network. When the reference signal is interrupted, the trained RBF neural network is used to compensate the estimated value of CKF filter state, and then a new estimated state is obtained. The cooperative localization experiment with the input error of multi-AUV cooperative localization system was simulated based on the lake area test data. The experimental results show that the average positioning error of the proposed method is reduced by 70% compared to average positioning error of RBF without CKF. Key

Key words: autonomousunderwatervehicle, cooperativelocaliztion, radialbasisfunction, cubatureKalmanfilter

中图分类号:

TB568

徐博，李盛新，金坤明，王连钊. 基于径向基函数神经网络辅助容积卡尔曼滤波的多自主水下航行器协同定位方法[J]. 兵工学报, 2019, 40(10): 2119-2128.

XU Bo, LI Shengxin, JIN Kunming, WANG Lianzhao. A Cooperative Localization Method for AUVs Based on RBF Neural Network-assisted CKF[J]. Acta Armamentarii, 2019, 40(10): 2119-2128.

参考文献

［1］刘明雍. 水下航行器协同导航技术［M］. 北京: 国防工业出版社, 2014:120-182.
LIU M Y. Cooperative navigation technology of underwater vehicle［M］. Beijing: National Defense Industry Press, 2014:120-182.(in Chinese)
［2］刘亚龙. 多水下航行器协同定位算法研究［D］. 哈尔滨:哈尔滨工程大学, 2015.
LIU Y L. Research on cooperative localization algorithm for multiple autonomous underwater vehicles［D］. Harbin:Harbin Engineering University, 2015.(in Chinese)
［3］ TAN X, LI J T. Cooperative positioning in underwater sensor networks［J］. IEEE Transactions on Signal Processing, 2010, 58(11): 5860-5871.
［4］ HUANG Y, ZHANG Y, XU B, et al. A new outlier-robust Student's t based Gaussian approximate filter for cooperative localization［J］. IEEE/ASME Transactions on Mechatronics, 2017, 22(5): 2380-2386.
［5］范颖, 张勇刚. 一种基于最大互相关熵容积卡尔曼滤波的AUV协同导航方法［C］∥2018惯性技术发展动态发展方向研讨会文集. 北京:中国惯性技术学会, 2018:7.
FAN Y, ZHANG Y G. An auv cooperative navigation method based on maximum correntropy cubature Kalman filter［C］∥2018 Inertial Technology Development Dynamic Development Direction Seminar Collection. Beijing: Chinese Society of Inertial Technology, 2018:7.(in Chinese)
［6］李闻白, 刘明雍, 李虎雄. 基于单领航者相对位置测量的多AUV协同导航系统定位性能分析［J］. 自动化学报, 2011(6): 724-736.
LI W B, LIU M Y, LI H X. Localization performance analysis of cooperative navigation system for multiple AUVs based on relative position measurements with a single leader［J］. Acta Automatica Sinica, 2011(6):724-736.(in Chinese)
［7］ MA C, ZHAO L, MEI X, et al. Thermal error compensation of high-speed spindle system based on a modified BP neural network［J］. International Journal of Advanced Manufacturing Technology, 2016, 89(9/10/11/12):1-15.
［8］李松, 汪圣利. 基于BP神经网络的非线性滤波算法研究［J］. 电子测量技术, 2018, 41(12):34-39.
LI S, WANG S L. Research of nonlinear filtering algorithm based on BP neutal network［J］. Electronic Measurement Technology, 2018, 41(12):34-39.(in Chinese)
［9］ XI Y H, PENG H. MLP training in a self-organizing state space model using unscented Kalman particle filter［J］. IEEE Transactions on Systems Engineering and Electronics, 2013, 24(1):141- 146.

［10］金保明, 颜望栋, 张烜, 等. 基于径向基函数神经网络的洪水预报方法［J］. 南昌大学学报(工科版), 2018, 40(3):246-252.
JIN B M, YAN W D, ZHANG H, et al. Flood forecast method based on radial basis function neural network［J］. Journal of Nanchang University (Engineering Edition), 2018, 40(3):246-252. (in Chinese)
［11］孙枫, 唐李军. Cubature卡尔曼滤波与Unscented卡尔曼滤波估计精度比较［J］. 控制与决策, 2013, 28(2):303-308.
SUN F, TANG L J. Estimation precision comparison of cubature Kalman filter and unscented Kalman filter［J］. Control and Decision, 2013, 28(2):303-308.(in Chinese)
［12］占荣辉, 张军. 非线性理论与目标跟踪［M］. 北京: 国防工业出版社, 2013:77-90.
ZHAN R H, ZHANG J. Nonlinear theory and target tracking［M］. Beijing: National Defend Industry Press, 2013:77-90.(in Chinese)
［13］胡振涛, 袁光耀, 胡玉梅, 等. 基于容积卡尔曼滤波的神经网络训练算法［J］. 控制与决策, 2016, 31(2):355-360.
HU Z T, YUAN G Y, HU Y M, et al. Training method of neural network based on cubature Kalman filter［J］. Control and Decision, 2016, 31(2):355-360.(in Chinese)
［14］ SIMON D J. Optimal state estimation: Kalman, H_∞, and nonlinear approaches［M］. Hoboken, NJ, US: John Wiley & Sons, 2006:333-369.
［15］ ARASARATNAM I, HAYKIN S. Cubature Kalman filters［J］. IEEE Transactions on Automatic Control, 2009, 54(6):1254-1269.
［16］ JULIER S J, UHLMAN J K. Unscented filtering and nonlinear estimation［J］. Proceedings of the IEEE, 2009, 54(6):1254-1269.
［17］ WANG W, CHEN X. Application of improved 5th-cubature Kalman filter in initial strapdown inertial navigation system alignment for large misalignment angles［J］. Sensors, 2018, 18(2):659.
［18］张良均, 曹晶, 蒋世忠. 神经网络实用教程［M］. 北京:机械工业出版社, 2008.2:37-40
ZHANG L J, CAO J, JIANG S Z. Neural network practical course［M］. Beijing:China Machine Press, 2008.2:37-40.(in Chinese)
［19］ SESHAGIRI S, KHALIL H K. Output feedback control of nonlinear systems using RBF neural networks［J］. IEEE Transactions on Neural Networks, 2000, 11(1):69-79.
［20］ WU Y Z, YIN Q, JIE H X, et al. A RBF-based constrained global optimization algorithm for problems with computationally expensive objective and constraints［J］. Structural & Multidisciplinary Optimization, 2018(1):1-23.
［21］ XU B, LI S X, RAZZAQI A A, et al. Cooperative localization in harsh underwater environment based on the MC-ANFIS［J］. IEEE Access, 2019(7):55407-55421.

第40卷
第10期2019 年10月兵工学报ACTA
ARMAMENTARIIVol.40No.10Oct.2019

[1]	张家闻，房浩霖，李家旺. 基于复杂约束条件的欠驱动AUV三维路径规划[J]. 兵工学报, 2022, 43(6): 1407-1414.
[2]	励明君，姜毅，马立琦，潘霄. 基于神经网络算法的发射场坪承载能力预测方法[J]. 兵工学报, 2022, 43(5): 982-991.
[3]	刘月, 刘铁林, 姜相争, 韩月明. 基于径向基函数和自组织映射的导弹控制系统健康状态评估[J]. 兵工学报, 2022, 43(4): 931-939.
[4]	张通彤, 姜湖海, 岳巍, 司晨, 袁满. 基于径向基函数神经网络的光电系统自适应控制[J]. 兵工学报, 2022, 43(3): 556-564.
[5]	陈林秀，郝明瑞，赵佳佳. 混合噪声条件下的目标被动定位算法[J]. 兵工学报, 2021, 42(9): 1923-1930.
[6]	卢雨，衣晓. 基于动态规划和双变量容积卡尔曼滤波的空基外辐射源定位算法[J]. 兵工学报, 2021, 42(4): 808-816.
[7]	王宁，李银伢，戚国庆，盛安冬. 不完全量测下基于信息一致性的分布式容积卡尔曼滤波算法[J]. 兵工学报, 2021, 42(11): 2396-2408.
[8]	邸青，周竞烨，方凯，姚佳琪，李家旺. 基于模型参数不确定的欠驱动非对称自主水下航行器全局镇定控制研究[J]. 兵工学报, 2020, 41(5): 950-957.
[9]	盛亮，邱志明，于邵祯，焦俊杰. 自主水下航行器多终点航路规划的距离正则化混合水平集算法研究[J]. 兵工学报, 2020, 41(4): 750-762.
[10]	赵建博，杨树兴，熊芬芬. 基于领弹-从弹架构的无导引头导弹协同定位与制导方法[J]. 兵工学报, 2019, 40(4): 673-679.
[11]	王金强，王聪，魏英杰，张成举. 未知海流干扰下自主水下航行器位置跟踪控制策略研究[J]. 兵工学报, 2019, 40(3): 583-591.
[12]	李彬，庞永杰，朱枭猛，程妍雪. 水下航行器环肋复合材料耐压壳6σ优化设计[J]. 兵工学报, 2018, 39(6): 1171-1177.
[13]	梁苑，盛安冬，武兆斌，张蛟，戚国庆，李银伢. 事件触发容积卡尔曼滤波及其在火控探测网络中的应用[J]. 兵工学报, 2018, 39(3): 417-427.
[14]	杜晓旭，张正栋. 自主水下航行器回收过程中螺旋桨推力特性分析[J]. 兵工学报, 2017, 38(6): 1154-1160.
[15]	江梦洁，李家旺，吕艳芳，周家炜，黄汉涛. 饱和输入限制下欠驱动自主水下航行器水平面航迹跟踪控制[J]. 兵工学报, 2017, 38(11): 2207-2213.