自主無人水面載具在海洋勘探和軍事發展中有多種應用。可以預見，隨著時間的推移，自主無人水面載具在未來海上環境開發中的利用將不斷提升，因此如何實現其準確的運動控制和自主導航能力為一大課題。得益於Mathwork公司的MALAB套裝軟體，設計導引律中常用的數學問題都有相應之函式可以提供設計者快速調用與驗證，目前水面無人載具的導引律(Guidance Law)設計已經十分成熟。本研究考慮一艘水面無人載具之非線性模型，導引律需要的軌跡使用三次樣條差值法來產生，將水面無人載具的導引律進行動力分配，利用最小平方法合理分配期望的控制力至船體上的不同致動器，並透過實驗或程式模擬收集各個致動器的輸入輸出資料，利用線性近似與類神經網路的方法來建立每個致動器的數學模型。此外，本研究根據致動器在船體上的位置，建立船體致動器的動力轉移矩陣，並計算其秩，以判斷船體可控制的維度。本研究將會採用一艘1.72公尺的水面載具，且配置2個可轉動之推進器，並達成自主無人水面載具動力分配的實現。而此論文將會有以下三項成果：1. 推導期望的控制力至船體上的不同致動器 2. 使用類神經網路的方法來建立致動器的數學模型、3. 實現水面無人載具之自主導控。

Autonomous unmanned surface vehicles (AUSVs) have various applications in marine exploration and military development. It is foreseeable that the utilization of AUSVs in future maritime environmental development will continue to enhance over time. Therefore, achieving precise motion control and autonomous navigation capabilities for AUSVs is a major challenge. Thanks to MathWorks' MATLAB software, there are corresponding functions available to designers for quick access and verification of commonly used mathematical problems in guidance law design. The design of guidance laws for unmanned surface vehicles is well-established. In this study, we consider a nonlinear model of an AUSV and generate the desired trajectory for the guidance law using cubic spline interpolation. The control allocation for the AUSV is carried out by distributing the desired control forces to different actuators on the AUSV using a least-squares method. The input-output data of each actuator are collected through experiments or program simulations, and mathematical models for each actuator are established using linear approximation and artificial neural networks. Additionally, based on the positions of the actuators on the AUSV, a thrust configuration matrix is constructed to calculate its rank, determining the controllable dimensions of the AUSV. This research employs a 1.72-meter AUSV equipped with two steerable thrusters to achieve the implementation of control allocation in autonomous unmanned surface vehicles. The thesis will present the following three contributions: 1. Deriving the desired control forces for different actuators on the AUSV, 2. Establishing mathematical models for the actuators using artificial neural networks, and 3. Achieving autonomous control and navigation of the unmanned surface vehicle.

[1] J. Wang, W. Gu, J. Zhu, and J. Zhang, ‘‘An unmanned surface vehicle for multi-mission applications,’’ in Proc. Int. Conf. Electron. Comput. Technol., Feb. 2009, pp. 358–361.
[2] M. Neal, T. Blanchard, A. Hubbard, N. Chauché, R. Bates, and J. Woodward, ‘‘A hardware proof of concept for a remote-controlled glacier-surveying boat,’’ J. Field Robot., vol. 29, no. 6, pp. 880–890,Nov. 2012.
[3] G. N. Roberts, “Trends in marine control systems,” Annu. Rev. Control, vol. 32, no. 2, pp. 263–269, 2008.
[4] Y. Shi, C. Shen, H. Fang, and H. Li, “Advanced control in marine mechatronic systems: A survey,” IEEE/ASME Trans. Mechatron., vol. 22, no. 3, pp. 1121–1131, Jun. 2017.
[5] E. Zereik, M. Bibuli, N. Miškovic, P. Ridao, and A. M. Pascoal, ´“Challenges and future trends in marine robotics,” Annu. Rev. Control, vol. 46, pp. 350–368, Dec. 2018.
[6] C. S. Chin, M. W. S. Lau, E. Low, and G. G. L. Seet, "A cascaded nonlinear heading control with thrust allocation: An application on an underactuated remotely operated vehicle," 2006 IEEE Conference on Robotics, Automation and Mechatronics, pp. 1-6, 2006.
[7] S. Ji, J. Jang, J. Jeong, and Y. Kim, "The H controller design including control allocation for marine vessel," 2012 12th International Conference on Control, Automation and Systems, pp. 1905-1907, 2012.
[8] T. A. Johansen and T. I. Fossen, "Control allocation - A survey," Automatica, vol. 49, pp. 1087-1103, 2013.
[9] M. W. Oppenheimer, D. B. Doman, and M. A. Bolender, "Control Allocation for Over-actuated Systems," 2006 14th Mediterranean Conference on Control and Automation, pp. 1-6, 2006.
[10] Fossen, Thor I., and Tor A. Johansen. "A survey of control allocation methods for ships and underwater vehicles." Control and Automation, 2006. MED'06. 14th Mediterranean Conference on. IEEE, 2006.
[11] Webster, William C., and Joao Sousa. "Optimum allocation for multiple thrusters." Proc. of the Int. Society of Onshore and Polar Engineers Conference (ISOPE’99). 1999.
[12] Johansen, Tor Arne, Thor I. Fossen, and Stig P. Berge. "Constrained nonlinear control allocation with singularity avoidance using sequential quadratic programming." Control Systems Technology, IEEE Transactions on 12.1 (2004): 211-216.
[13] Yadav, Parikshit, et al. "Optimal Thrust Allocation for Semisubmersible Oil Rig Platforms Using Improved Harmony Search Algorithm." Oceanic Engineering, IEEE Journal of 39.3 (2014): 526-539.
[14] T. I. Fossen, “Guidance and Control of Ocean Vehicles”, John Wiley and Sons, 5-91, 1994.
[15] M. M. Hammad, A. K. Elshenawy, and M. I. El Singaby, "Trajectory following and stabilization control of fully actuated AUV using inverse kinematics and self-tuning fuzzy PID," PLOS ONE, vol. 12, no. 7, pp. 951-953, 2017.
[16] T. I. Fossen, "Marine control systems–guidance. navigation, and control of ships, rigs and underwater vehicles," Marine Cybernetics, Trondheim, Norway, Org. Number NO 985 195 005 MVA, www. marinecybernetics. com, ISBN: 82 92356 00 2, 2002.
[17] W.-M. Hu, " Nonlinear H2 and H∞ Control Law Designs of Autonomous Unmanned Surface Vessels", Master Degree, Systems and Naval Mechatronic Engineering, National Cheng Kung University, Tainan, Taiwan, 2014.