Технологии интеллектуальных вычислений в задачах повышения точности интегрированных навигационных систем

Недостатки фильтра Калмана как единственного устройства для интеграции инерциальных и спутниковых навигационных систем мотивировали исследования в области реализации альтернативных методов их интеграции преимущественно на основе интеллектуальных вычислений. За последние 15 лет проведены исследования для изучения возможности использования методов интеллектуальных вычислений в области интегрированных инерциальных и спутниковых навигационных систем. Применены различные подходы к объединению модулей интеллектуальных вычислений с остальными частями инерциальных и спутниковых навигационных систем. В результате предложено несколько схем, структура которых варьируется в зависимости от типа модулей интеллектуальных вычислений и их роли в инерциальных и спутниковых навигационных системах. Предложена классификация интеллектуальных схем оценки навигационной информации на основе их структурных особенностей и принципов функционирования. Проведен сравнительный анализ эффективности алгоритмов интеллектуальных вычислений с позиции возможности их реализации в инерциальных и спутниковых навигационных системах и точностных характеристик. Отмечены некоторые аспекты, которые необходимо учитывать в перспективных работах в этой области

Литература

[1] Grewal M.S., Weill L.R., Andrews A.P. Global positioning systems, inertial navigation, and integration. John Wiley & Sons, 2007.

[2] Hofmann-Wellenhof B., Lichtenegger H., Wasle E. GNSS - global navigation satellite systems: GPS, GLONASS, Galileo, and more. Springer, 2008.

[3] Farrell J., Barth M. The global positioning system and inertial navigation. McGraw-Нill, 1999.

[4] Матвеев В.В. Инерциальные навигационные системы. Тула, Изд-во ТулГУ, 2012.

[5] Матвеев В.В., Распопов В.Я. Основы построения бесплатформенных инерциальных навигационных систем. СПб., ОАО «Концерн «ЦНИИ «Электроприбор», 2009.

[6] Brown R.G., Hwang P.Y. Introduction to random signals and applied Kalman filtering: with MATLAB. Exercises and solutions. Wiley, 1997.

[7] Crassidis J.L., Junkins J.L. Optimal estimation of dynamic systems. CRC press, 2011.

[8] Vanicek P., Omerbasic M. Does a navigation algorithm have to use a Kalman filter? CASI, 1999, vol. 45, no. 3, pp. 292–296.

[9] Sharaf R., Taha M., Tarbouchi M., et al. Merits and limitations of using fuzzy inference system for temporal integration of INS/GPS in vehicular navigation. Soft Comput., 2007, vol. 11, iss. 9, pp. 889–900. DOI: 10.1007/s00500-006-0140-0

[10] Потапов А.С. Технологии искусственного интеллекта. СПб., СПбГУ ИТМО, 2010.

[11] Haykin S. Neural networks: a comprehensive foundation. Prentice Hall, 1998.

[12] Eiben A.E., Smith J.E. Introduction to evolutionary computing. Springer, 2003.

[13] Giarratano J.C., Riley G. Expert systems: principles and programming. Brooks/Cole, 1989.

[14] Mitchell M. An introduction to genetic algorithms. MIT Press, 1998.

[15] Chiang K.-W., Noureldin A., El-Sheimy N. A new weights updating method for neural networks based INS/GPS integration architectures. Meas. Sci. Technol., 2004, vol. 15, no. 10, pp. 2053–2061. DOI: 10.1088/0957-0233/15/10/015

[16] El-Sheimy N., Chiang K.-W., Noureldin A. The utilization of artificial neural networks for multisensor system integration in navigation and positioning instruments. IEEE Trans. Instrum. Meas., 2006, vol. 55, no. 5, pp. 1606–1615. DOI: 10.1109/TIM.2006.881033

[17] Noureldin A., Osman A., El-Sheimy N. A neuro-wavelet method for multi-sensor system integration for vehicular navigation. Meas. Sci. Technol., 2003, vol. 15, no. 2, pp. 404–412. DOI: 10.1088/0957-0233/15/2/013

[18] Noureldin A., El-Shafie A., El-Sheimy N. Adaptive neuro-fuzzy module for inertial navigation system/global positioning system integration utilising position and velocity updates with real-time cross-validation. IET Radar, Sonar Nav., 2007, vol. 1, iss. 5, pp. 388–396. DOI: 10.1049/iet-rsn:20070001

[19] Chiang K.W., Noureldin A., El-Sheimy N. Constructive neural-networks-based MEMS/GPS integration scheme. IEEE Trans. Aerosp. Electron. Syst., 2008, vol. 44, iss. 2, pp. 582–594. DOI: 10.1109/TAES.2008.4560208

[20] Fahlman S.E., Lebiere C. The cascade-correlation learning architecture. Advances in Neural Information Processing Systems, 1990, vol. 2, pp. 524–532.

[21] Breiman L. Random forests. Machine Learning, 2001, vol. 45, iss. 1, pp. 5–32. DOI: 10.1023/A:1010933404324

[22] Adusumilli S., Bhatt D., Wang H., et al. A low-cost INS/GPS integration methodology based on random forest regression. Expert Syst. Appl., 2013, vol. 40, iss. 11, pp. 4653–4659. DOI: 10.1016/j.eswa.2013.02.002

[23] More J.J. The Levenberg - Marquardt algorithm: implementation and theory. In: Numerical analysis. Springer, 1978, pp. 105–116.

[24] Sharaf R., Noureldin A., Osman A., et al. Online INS/GPS integration with a radial basis function neural network. IEEE Aerosp. Electron. Syst. Mag., 2005, vol. 20, iss. 3, pp. 8–14. DOI: 10.1109/MAES.2005.1412121

[25] Sharaf R., Noureldin A. Sensor integration for satellite-based vehicular navigation using neural networks. IEEE Trans. Neural Netw., 2007, vol. 18, iss. 2, pp. 589–594. DOI: 10.1109/TNN.2006.890811

[26] Jang J.-S.R. ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans. Syst., Man, Cybern., 1993, vol. 23, iss. 3, pp. 665–685. DOI: 10.1109/21.256541

[27] Taha M.R., Noureldin A., El-Sheimy N. Improving INS/GPS positioning accuracy during GPS outages using fuzzy logic. Proc. 16th Int. Tech. Meeting of the Satellite Division of the Inst. of Navigation (ION GPS/GNSS 2003). Portland, 2003, pp. 499–508.

[28] Bezdek J.C. Objective function clustering. In: Pattern recognition with fuzzy objective function algorithms. Springer, 1981, pp. 43–93.

[29] Noureldin A., El-Shafie A., Taha M.R. Optimizing neuro-fuzzy modules for data fusion of vehicular navigation systems using temporal cross-validation. Eng. Appl. Artif. Intel., 2007, vol. 20, iss. 1, pp. 49–61. DOI: 10.1016/j.engappai.2006.03.002

[30] Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. IJCAI, 1995, vol. 14, no. 2, pp. 1137–1145.

[31] Hasan A.M., Samsudin K., Ramli A.R., et al. Automatic estimation of inertial navigation system errors for global positioning system outage recovery. J. Aerospace Eng., 2011, vol. 225, iss. 1, pp. 86–96. DOI: 10.1243/09544100JAERO731

[32] Hasan A.M., Samsudin K., Ramli A.R. Optimizing of ANFIS for estimating INS error during GPS outages. J. Chin. Inst. Eng., 2011, vol. 34, iss. 7, pp. 967–982. DOI: 10.1080/02533839.2011.591970

[33] Kennedy J. Particle swarm optimization. In: Encyclopedia of machine learning. Springer, 2011, pp. 760–766.

[34] Hou H., El-Sheimy N. Inertial sensors errors modeling using Allan variance. Proc. 16th Int. Tech. Meeting of the Satellite Division of the Inst. of Navigation (ION GPS/GNSS 2003). Portland, 2016, pp. 1209–1213.

[35] Goodall C., Syed Z., El-Sheimy N. Improving INS/GPS navigation accuracy through compensation of Kalman filter errors. IEEE Veh. Tech. Conf., 2006, pp. 1090–3038. DOI: 10.1109/VTCF.2006.578

[36] Abdel-Hamid W., Noureldin A., El-Sheimy N. Adaptive fuzzy prediction of low-cost inertial-based positioning errors. IEEE Trans. Fuzzy Syst., 2007, vol. 15, iss. 3, pp. 519–529. DOI: 10.1109/TFUZZ.2006.889936

[37] Noureldin A., Karamat T.B., Eberts M.D., et al. Performance enhancement of MEMS-based INS/GPS integration for low-cost navigation applications. IEEE Trans. Veh. Tech., 2009, vol. 58, iss. 3, pp. 1077–1096. DOI: 10.1109/TVT.2008.926076

[38] Wang J.J., Wang J., Sinclair D., et al. Neural network aided Kalman filtering for integrated GPS/INS geo-referencing platform. 5th Symp. Mobile Mapping Tech., 2007. pp. 1–6.

[39] Chen L., Fang J. A hybrid prediction method for bridging GPS outages in high-precision POS application. IEEE Trans. Instrum. Meas., 2014, vol. 63, iss. 6, pp. 1656–1665. DOI: 10.1109/TIM.2013.2292277

[40] Huang G.B., Wang D.H., Lan Y. Extreme learning machines: a survey. Int. J. Mach. Learn. & Cyber., 2001, vol. 2, iss. 2, pp. 107–122. DOI: 10.1007/s13042-011-0019-y

[41] Jingsen Z., Wenjie Z., Bo H., et al. Integrating extreme learning machine with Kalman filter to bridge GPS outages. ICISCE, Beijing, 2016, pp. 420–424. DOI: 10.1109/ICISCE.2016.98

[42] Kasabov N., Filev D. Evolving intelligent systems: methods, learning, and applications. 2006 Int. Symp. Evolv. Fuzzy Syst. Ambelside, United Kingdom, 2006, pp. 8–18.

[43] Boulton A. Data-driven learning: taking the computer out of the equation. Lang. Learn., 2010, vol. 60, iss. 3, pp. 534–572. DOI: 10.1111/j.1467-9922.2010.00566.x

[44] Schmidhuber J. Deep learning in neural networks: An overview. Neur. Networks, 2015, vol. 61, pp. 85–117. DOI: 10.1016/j.neunet.2014.09.003