首先，經由兩個垂直的天線從由三個標籤(Tags)所組成的三角形藉由 RFID 讀取器得到接收信號強度指標(RSSIs)，並藉由此 6 個 RSSIs 得到目標人物(TH)相對於無人搬運車(AGV)的姿態與方位角，由於輸入與輸出的關係有著非線性、耦合以及隨機的特性存在，所以先藉由具有單位直流增益的一階低通濾波器濾除RSSIs不需要的高頻訊號，再者藉由多層類神經網路(MLNN)的優勢，例如:隨機逼近、對雜訊較不敏感以及輸入和輸出數目可以不同等特性與 Levenberg-Marquard Back-Propagation (LMBP)學習法則結合並利用 6個濾波過的RSSIs與3的輸出(即姿態與方位角)來建構出多層感知類神經網路(MLPN)的模型，接著線上規劃軌跡且藉由 MLPN 的輸出來進行預測跟隨 TH。本論文使用階層式可變結構控制(HVSC)線上追蹤所規劃的路徑來達成跟隨 TH 的目的，為了有效執行此方法，使用軟硬體共同設計的平台(DE2i-150)來研發 MLPN 的建模、軌跡規劃以及 HVSC 的演算法，其中利用硬體端的控制訊號(例如:驅動馬達的 PWM)以及感測器的輸入(例如:馬達解碼器以及經由 USB 讀取的 RFID 訊號)，最後，本論文藉由多層類神經網路為主的RFID定位系統與HVSC演算法來驗證跟隨TH的有效性、效率以及穩健性。

At the beginning, the received signal strength indicators (RSSIs) of the three tags on a triangular pattern are read by two perpendicular antennas. These 6 RSSIs and their corresponding pose and the azimuth angle of target human (TH) with respect to automatic guided vehicle (AGV) are obtained. Since the relations of these pairs of input and output are nonlinear, coupled, and stochastic, it is difficult to obtain an effective model. A 1st-order low-pass filter with unit dc gain is first employed to remove the unnecessary high frequencies of RSSIs. Due to the advantageous features of neural network modeling, e.g., stochastic approximation, insensitive to noise, different numbers of input and output, the multilayer neural network (MLNN) with Levenberg-Marquard Back-Propagation (LMBP) learning law is employed to achieve the model between six filtered RSSIs and three outputs (i.e., the pose and the azimuth angle of TH). Then the trajectory to track the TH is on-line planned and predicted from the output of Multilayer Perceptron Network (MLPN). The hierarchical variable structure control (HVSC) is employed to on-line track the planning trajectory such that the TH following is achieved. For an effective implementation, a software/hardware based platform is employed to develop the software for the MLPN modeling, the trajectory planning algorithm and the HVSC algorithm, and the hardware for the control signal (e.g., the PWM for driving the motor) and for the sensor inputs (e.g., the decoder for obtaining the position or velocity of motor, the USB interface for receiving RFID signal). Finally, the experiments for the TH following by the proposed NN-based RFID localization system and HVSC algorithm confirm the effectiveness, efficiency, and robustness of the proposed method.

[1] K. Morioka, J. H. Lee, and H. Hashimoto, “Human-following mobile robot in a distributed intelligent sensor network,” IEEE Trans. Ind. Electron., vol. 51, no. 1, pp. 229–237, Feb. 2004.
[2] J. Pineau, M. Montemerlo, M. Pollack, N. Roy, and S. Thrun, “Towards robotic assistants in nursing homes: Challenges and results,” J. of Robot. Autonom. Syst., vol. 42, no. 3/4, pp. 271–281, Mar. 2003.
[3] J. S. Hu, C. W. Juan, and J. J. Wang, “A spatial-color mean-shift object tracking algorithm with scale and orientation estimation,” Pattern Recognit. Lett., vol. 29, no. 16, pp. 2165–2173, Dec. 2008.
[4] G. Courtine and M. Schieppati, “Human walking along a curved path. I. Body trajectory, segment orientation and the effect of vision,” Eur. J. Neurosci., vol. 18, no. 1, pp. 177–190, Jul. 2003.
[5] G. Arechavaleta, J. P. Laumond, H. Hicheur, and A. Berthoz, “An optimality principle governing human walking,” IEEE Trans. Robot., vol. 24, no. 1, pp. 5–14, Feb. 2008.
[6] N. Belotto and H. Hu, “Multisensor-based human detection and tracking for mobile service robots,” IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 39, no. 1, pp. 167–181, Feb. 2009.
[7] K. Kobayashi and S. Yamada, “Extending commands embedded in actions for human–robot cooperative tasks,” Int. J. Social Robot., vol. 2, no. 2, pp. 159–173, Jun. 2010.
[8] W. Chung, H. Kim, Y. Yoo, C. Moon, and J. Park, “The detection and following of human legs through inductive approaches for a mobile robot with a single laser range finder,” IEEE Trans. Ind. Electron., vol. 59, no. 8, pp. 3156–3166, Aug. 2012.
[9] V. Alvarez-Santos, X. Pardo, R. Iglesias, A. Canedo-Rodriguez, and C. Regueiro, “Feature analysis for human recognition and discrimination: Application to a person following behaviour in a mobile robot,” Robot. Autonom. Syst., vol. 60, no. 8, pp. 1021–1036, Aug. 2012.
[10] J. S. Hu, J. J. Wang, and D. M. Ho, “Design of sensing system and anticipative behavior for human following of mobile robots,” IEEE Trans. Ind. Electron. vol. 61, no. 4, pp. 1916-1927, Arp. 2014.
[11] D. Fortin-Simard, J. S. Bilodeau, K. Bouchard, S. Gaboury, B. Bouchard, and A. Bouzouane, “Exploiting passive RFID technology for activity recognition in smart homes,” IEEE Intelligent Systems, to be appeared, 2016.
[12] S. S. Saab and Z. S. Nakad, “A standalone RFID indoor positioning system using passive tags,” IEEE Trans. Ind. Electron., vol. 58, no. 5, pp. 1961-1970, May 2011.
[13] E. DiGiampaolo and F. Martinelli, “A passive UHF-RFID system for the localization of an indoor autonomous vehicle,” IEEE Trans. Ind. Electron., vol. 59, no. 10, pp. 3961-3970, Oct. 2012.
[14] E. DiGiampaolo and F. Martinelli, “Mobile robot localization using the phase of passive UHF RFID signals,” IEEE Trans. Ind. Electron., vol. 61, no. 1, pp. 361-376, Oct. 2014.
[15] J. J. Pomárico-Franquiz, M. Granados-Cruz, and Y. S. Shmaliy, “Self-localization over RFID tag grid excess channels using extended filtering techniques,” IEEE Journal of Selected Topics in Signal Processing, vol. 9, no. 2, pp. 229-238, Mar. 2015.
[16] S. S. Saab and H. Msheik, “Novel RFID-based pose estimation using single stationary antenna,” IEEE Trans. Ind. Electron., vol. 63, no. 3, pp. 1842-1852, Mar. 2016.
[17] H.Y. Yu, J. J. Chen, and T. R. Hsiang, “Design and implementation of a real-time object location system based on passive RFID tags,” IEEE Sensor Journal, 2016, vol. 15, no. 9, pp. 5015-5021, Sep. 2016.
[18] C. H. Huang, L. H. Lee, C. C. Ho, L. L. Wu, and Z. H. Lai, “Real-time RFID indoor positioning System based on Kalman-filter drift removal and Heron-bilateration location estimation,” IEEE Trans. Instrum. & Meas. to be appeared, 2016.
[19] S. Haykin, Neural Networks and Learning Machines, Pearson Education Inc., 3rd Ed., 2009.
[20] C. L. Hwang, Y. J. Chou, and C. W. Lan, ““Search, track and kick to virtual target point” of humanoid robots by a neural-network-based active embedded vision system,” IEEE Syst. Journal, vol. 9, no. 1, pp. 107-118, Mar. 2015.
[21] C. L. Hwang and H. M. Wu, “Trajectory tracking of a mobile robot with frictions and uncertainties using hierarchical sliding-mode under-actuated control,” IET Contol Theory & Applications, vol. 7, no. 7, pp. 952-965, 2013.
[22] Z. Hajduk, B. Trybus, and J. Sadolewski, “Architecture of FPGA embedded multiprocessor programmable controller,” IEEE Trans. Ind. Electron., vol. 62, no. 5, pp. 6952-6961, May 2015.