車載移動式測繪系統(MMSs)已被廣泛應用於獲取空間資訊，三維數碼城市即為一例。現今最普遍用於MMS的技術即利用全球衛星定位系統(GPS)作為主要定位感測器和慣性導航系統(INS)作為主要定向感測器。卡曼濾波器(KF)的限制和多感測器系統整體的花費已然侷限了大多數陸基式MMS應用的普及性。為了提升低價微機電系統(MEMS)慣性量測單元(IMU)和GPS之執行效率，由多層前饋類神經網路(MFNs)和平滑器(smoother)組成的智慧型定位定向感測器策略已被提出，但MFNs的自動化並不如最初預期的容易。

因此，本研究不僅解決了前人研究提出應用於 MEMS IMU/GPS 整合系統MFN-smoother 演算法自動化程度不足的問題，也提出並分析以更自動化的方式整合數種感測器的替代型智慧定位定向策略。本研究所提出的演算法利用構造型類神經網路稱作動態反傳類神經網路(DBPNs)來克服傳統平滑器演算法和先前提出的MFN-smoother策略的不足。所應用的DBPNs相較於MFNs也有著諸如具備較為彈性的位相等優點。本研究初步的研究成果顯示，就本研究的實驗資料而言，所提出的策略比平滑器演算法和MFN-smoother 策略都來的有效。同時，所提出的策略也利用兩個連續時間瞬刻位置和姿態元素的差值作為類神經網路的輸入來減低因為地理相依性所造成的影響。

Mobile mapping systems (MMSs) have been widely applied for acquiring spatial information in applications such as 3D city models. Nowadays the most common technologies used for positioning and orientation of a mobile mapping system include using Global Positioning System (GPS) as a major positioning sensor and Inertial Navigation System (INS) as the major orientation sensor. The limitation of Kalman Filter (KF) and the price of overall multi-sensor systems have limited the popularization of most land-based mobile mapping applications. Although intelligent sensor positioning and orientation schemes have been proposed consisting of Multi-layer Feed-forward Neural Networks (MFNs) and smoother, in order to enhance the performance of a low cost Micro Electro Mechanical Systems (MEMS) Inertial Measurement Unit (IMU) and GPS integrated system, the automation of the MFN applied is not as easy as initially expected.

Therefore, this study not only addresses the problems of insufficient automation in the conventional methodology that has been applied in MFN-smoother algorithms for MEMS IMU/GPS integrated systems proposed in previous studies, but also exploits and analyzes the idea of developing alternative intelligent sensor positioning and orientation schemes that integrate various sensors in more automatic ways. The proposed schemes are implemented using one of the most famous constructive neural networks: Dynamic Back Propagation Neural Networks (DBPNs), to overcome the limitations of conventional techniques based on the smoother algorithms as well as previously developed MFN-smoother schemes. The DBPNs applied also have the advantage of a more flexible topology compared to the MFNs. The preliminary results presented in this research illustrate the effectiveness of the proposed schemes over smoother algorithms as well as the MFN-smoother schemes based on the experimental data utilized in this study. The proposed scheme also applies the increments of position and orientation states between consecutive epochs as the input of the network to reduce the impact of geographical dependence.

Aggarwal, P.: Hybrid Extended Particle Filter (HEPF) for INS/GPS Integrated System, Proceedings of ION GNSS 2008, Savannah, Georgia, September 16-19, 2008.

Barto, A.G., Bradtke, S.J., and Singh, S.: Learning to act using real time dynamic programing, Artificial Intelligence, vol.72,pp.81-138, 1995.

Bar-Shalom, Y., Li, X.R., and Kirubarajan, T.: Estimation with Applications to Tracking and Navigation, John Wiley & Sons, Inc., 2001.

Bergman, N.: Recursive Bayesian Estimation Navigation and Tracking Applications. Sweden: Dissertation Nr. 579, Linköping University, 1999.

Bishop, C.M.: Neural Networks for Pattern Recognition, Oxford University Press, New York, NY, USA, 1995.

Brown, R.G. and Hwang, P.Y.C.: Introduction to Random Signals and Applied Kalman Filtering, John Wiley & Sons Inc., 1997.

Chang, H.W.: The Development of self-growing Neural Network Embedded POS Determination Scheme for MEMS INS/GPS Integrated Systems, Master thesis, Department of Geomatics, National Cheng Kung University, 2009.

Chiang, K.W., Noureldin, A., El-Sheimy, N.: A New Weight Updating Method for INS/GPS Integration Architectures Based on Neural Networks. Meas. Sci. Technol, 15, 2053-2061, 2003.

Chiang, K.W., Noureldin, A., El-Sheimy, N.: Multi-sensors integration using neuron computing for land vehicle navigation. GPS Solutions 2003, 6(3):209–218, 2003.

Chiang, K.W.: INS/GPS Integration Using Neural Networks for Land Vehicular Navigation Applications, Department of Geomatics Engineering, the University of Calgary, Calgary, Canada, 2004.

Chiang, K.W. and Chang, H.W.: Intelligent Sensor Positioning and Orientation Through Constructive Neural Network-Embedded INS/GPS Integration Algorithms, Department of Geomatics, National Cheng-Kung University, Sensors, pp.9252-9285, 2010.

Crassidis, J.L. and Junkins, J.L.: Optimal Estimation of Dynamic Systems, Chapman & Hall/CRC, 2004.

Daniel, R.: Inertial and Magnetic Sensing of Human Motion. PhD thesis, Universiteit Twente, 2006.

Doucet, A., De Freitas, N., Gordon, N.: Sequential Monte Carlo Methods in Practice. Springer, 2001.

El-Sheimy, N.: Introduction to Inertial Navigation. ENGO 699.71 Lecture Notes, Geomatics Department, University of Calgary, Calgary, Canada, 2002.

El-Sheimy, N., Abdel-Hamid, W., Lachapelle, G.: An Adaptive Neuro-Fuzzy Model for Bridging GPS Outages in MEMS-IMU/GPS Land Vehicle Navigation, Proceedings of ION GNSS 2004, Long Beach, California, September 21-24, 2004.

El-Sheimy, N.: Inertial Techniques and INS/DGPS Integration. ENGO623-Course Notes, Department of Geomatics Engineering, The University of Calgary, Canada, 2007.

Fahlman, S.E. and Lebiere, C.: The cascade learning Architecture, In D.S. Touretzky (Ed.), Advances in Neural Information Processing System 2, Denver, CO, Morgan Kaufmann Puvlishers, p.198-209, 1990.

Fahlman, S.E. and Lebiere, C.: The cascade-correlation learning architecture Advances in Neural Information Processing Systems vol. 2 (San Mateo, CA: Morgan Kaufmann), pp. 524–32, 1991.

Fredric, M.H. and Ivica, K.: Principles of Neurocomputing for Science and Engineering, 2001.

Gibbons, G.: China GNSS 10. Compass in the rearview mirror. InsideGNSS, January/February, p. 62-63, 2008.

Gelb, A.: Applied Optimal Estimation, The M.I.T. Press, Cambridge, MA, USA, 1974.

Goodall, C., El-Sheimy, N., Chiang, K.W.: The Development of a GPS/MEMS INS Integrated System Utilizing a Hybrid Processing Architecture, Proceedings of ION GNSS 2005, Long Beach, California, September 13-16, 2005.

Gordon, N.J., Salmond, D.J., Smith, A.F.M.: Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proceedings F on Radar and Signal Processing, 1993, 140 (2): 107–113. doi:10.1049/ip-f-2.0015, 1993.

Grewal, M.S. and Andrews, A.P.: Kalman Filtering: Theory and Practice. Prentice-Hall, Inc., 2001.

Gustafsson, F., Gunnarsson, F., Bergman, N., Forssell, U., Jansson, J., Karlsson, K., Nordlund, P.J.: Particle filters for positioning, navigation and tracking, IEEE Transactions on Signal Processing, vol. 50, 425-437, 2002.

Haykin, S.: Neural Networks, A Comprehensive Foundation, second Edition, Prentice-Hall, New Jersey, 1999.

Haykin, S.: Neural Networks and Learning Machines, Third Edition, 2009.

Jansson, P.: Precise Kinematic GPS Positioning with Kalman Filtering and Smoothing: Theory and Application, Doctoral Dissertation, Division of Geodesy Report NO. 1048, Department of Geodesy and Photogrammetry, Royal Institute of Technology, Stockholm, Sweden, 1998.

Jay, A. F.: AIDED NAVIGATION: GPS with High Rate Sensors, pp.21, 2008.

Julier, S.J. and Uhlmann, J.K.: New extension of the Kalman filter to nonlinear systems, Proceedings of the SPIE, 182-193, 1997.
Kubo, Y. and Wang, J.: INS/GPS Integration Using Gaussian Sum Particle Filter, Proceedings of ION GNSS 2008, Savannah, Georgia, September 16-19, 2008.

Lapucha, D., Schwarz, K.P., Cannon, M.E., Martell, H.: The Use of GPS/INS in a Kinematic Survey System, Proc. IEEE, PLANS 1990, Las Vegas, March 20-23, 1990, pp. 413 – 420, 1990.

Lin, Y.C.: The Development of Hybrid INS/GPS Integration Schemes Using Artificial Neural Networks, Master thesis, Department of Geomatics, National Cheng Kung University, 2008.

Liu H. (Terry): Optimal Smoothing Techniques in Aided Inertial Navigation and Surveying Systems, Department of Geomatics Engineering, November, 2009.

Meditch, J.S.: Stochastic Optimal Linear Estimation and Control, McGraw-Hill, 1969.

Mendel, J.M. and McLaren, R.W.: Reinforcement-learning control and pattern recognition systems, in Adaptive, Learning, and Pattern Recognition Systems, Theory and Application, vol. 66. J.M. Mendel and K.S.Fu, eds., pp.287-318, New York: Academic Press, 1970.

Misra, P. and Enge, P.: Global Positioning System, Signals, Measurements and Performance, 2001.

Nassar, S., Shin, E., Niu, X. and El-Sheimy, N.: Accurate INS/GPS Positioning with Different Inertial Systems Using Various Algorithms for Bridging GPS Outages, Proceeding of International Technical Meeting of ION-GNSS, Long Beach, CA, U.S, 2005.

Oliver, J.W.: An introduction to inertial navigation. Technical Report Number 696, Computer Laboratory UCAM-CL-TR-696, ISSN 1476-2986, 2007.

Paul, D.G.: Principles of GNSS, Inertial, and Multisensor Integrated Navigation Systems. Groves, ISBN-13:978-1-58053-255-6, 2008.
Peter, S.K. and El-Sheimy N.: MOBILE MAPPING SYSTEMS – STATE OF THE ART AND FUTURE TRENDS, Department of Geomatics Engineering, University of Calgary, 2500 University Drive NW, Calgary, Alberta, T2N 1N4 Canada, 2005.

Rauch, H.E., Tung, F. and Striebel, C.T.: Maximum Likelihood Estimates of Linear Dynamic Systems, AIAA Journal, V.3, N.8, 1965.

Schwarz, K.P., Chapman, M.A., Cannon, M.E., Gong, P.: An Integrated INS/GPS Approach to the Georeferencing of Remotely Sensed Data. PE&RS, Vol. 59, No. 11, pp. 1667-1674, 1993.

Schwarz, K.P. and Wei, M.: INS/GPS Integration for Geodetic Applications, Lecture Notes ENGO 623, Department of Geomatics Engineering, The University of Calgary, Calgary, Canada,1999.

Sharaf, R. and Noureldin, A.: Sensor Integration for Satellite-Based Vehicular Navigation Using Neural Networks, IEEE TRANSACTIONS ON NEURAL NETWORKS, 18(2), 589-594, 2007.

Shin, E.H.: A Quaternion-Based Unscented Kalman Filter for the Integration of GPS and MEMS INS, Proceedings of ION GNSS 2004, Long Beach, California, September 21-24, 2004.

Sulej, R., Zaremba, K., Kurek, K. and Rondio, E.: Application of the neural networks in events classification in the measurement of the spin structure of the deuteron, Institute of Radio electronics, Warsaw University of Technology, Warsaw, Poland, Soltan Institute for Nuclear Studies, Warsaw, Poland, 2007.

Sulej, R., Zaremba, K., and Kurek, K.: Dynamic Topology Adjustment Algorithm for MLP Networks, Institute of Radioelectronics, Warsaw University of Technology, Warsaw, Poland, 2006.

Syed, Z., Aggarwal, P., El-Sheimy, N.: Hybrid Extended Particle Filter (HEPF) for Integrated Civilian Navigation System, Proceedings of IEEE/ION PLANS 2008, Monterey, California, May 6 – 8, 2008.

Tao, V. and Li, J.: Advances in Mobile Mapping Technology, International Society for Photogrammetry and Remote Sensing (ISPRS) Book Series, Taylor and Francis Group: London, U.K., 2007.

Thomas, L. and Metzger, J.: Ultra tightly coupled GNSS/INS navigation and requirements for future deeply coupled systems, Diehl BGT Defense, Germany, 2008.

Titterton, D.H. and Weston, J.L.: Strapdown Inertial Navigation Technology, Peter Peregrinus Ltd, 1997.

Van Der Merwe, R., Doucet, A., De Freitas, N., Wan, E.: The unscented particle filter, Advances in Neural Information Processing Systems (NIPS13), 584-590, 2000.

Wang, J. and Ding, W.: Improving Adaptive Kalman Filter in GPS/SDINS Integration with Neural Network, Proceedings of ION GNSS 2007, Fort Worth, Taxes, September 25-28, 2007.

Zhang, K.F. and Xiao B.L.: GPS and Mobile Multisensor Mapping System, WUJNS, Vol. 8, No. 2B, pp. 557-565, 2003.