無人機(Unmanned Aerial Vehicle)應用在監控系統中是近年來非常熱門的研究主題，因此如何在外在環境變動時對最佳能源效率路徑進行繪製，以及在路徑追蹤時進行能量消耗預測，仍是近些年的研究重點。本文中提出一個完整的具有能量消耗預測、最佳路徑規劃和抗擾控制功能的無人機監控系統，並以具有任務路徑規劃功能的的六旋翼無人機作為研究對象。首先，藉由彈性網絡迴歸(Elastic Net Regression)方法設計任務導向的無人機能源消耗預測黑盒子模型，此方法包含資料收集、資料預處理及回歸分析。為了取得所需之資料，需先定義各種飛行模式，並且蒐集執行飛行任務時之資料，其中包括全球定位系統(Global Positioning System)訊息及電池資料。再者，資料預處理需將無人機的運動軌跡分離成水平運動的加減速資料，在兩個不同的飛行模式下模擬從起飛到降落時之無人機監控任務，其結果與預測的能量消耗相比平均有98.773%的準確率。更進一步，經過訓練與測試回歸之模型將被當成最佳化路徑規劃方案的成本函數，其設計是根據分群後三維(3D)真實飛行之數據，且方案之結果通過本文提出的凝聚分類(k-Agglomerative Clustering)理論和運用A-star及具有自適應權重的集合式粒子群優化演算法(Set-based Particle Swarm Optimization)，得以提出具有最低能源消耗之最佳化路徑規劃。此外，本文亦發展具有可變學習率及線上學習能力之自適應類神經網路(Adaptive Neural Network)控制系統以駕馭無人機飛行軌跡，並驗證其對於干擾具快速且可靠之響應且有較小的追蹤誤差。在進行相同任務時，使用手動操控的路徑會消耗96.59瓦時(Wh)的耗電量，而使用本文提出的最佳路徑，則只需消耗76.037瓦時的耗電量。本文提出之自適應類神經網路控制與傳統比例積分微分控制和模糊控制相比，當外部干擾發生時能提高水平與垂直追蹤性能的均方根誤差達49.083%和37.50%。綜上所述，結合本文提出的能源消耗預測之最佳化路徑規劃方法與自適應類神經網路控制器，能夠提供無人機監控系統更有效的能源管理應用，且對於擾動的反應速度能更迅速。

A surveillance system is one of the most interesting research topics for an unmanned aerial vehicle (UAV). However, the problem of planning an energy-efficient path for the surveillance purpose while anticipating disturbances and predicting energy consumptions during the path tracking is still a challenging problem in recent years. In this thesis, a complete UAV energy consumption prediction, optimal path planning, and disturbance rejection control for a UAV surveillance system is investigated. The setup consists of ArduPilot with Mission Planner Firmware installed to a custom-built hexarotor. First, a mission-based black box modelling of UAV energy consumption prediction is designed via the elastic net regression. The method consists of three consecutive steps: data collection, data preprocessing, and regression. First, to collect the required data, flight patterns that contain several type of movements are defined where then the flight data log that contain missions, global position system (GPS), and battery information are collected. Afterward, the preprocessing includes the movement separation, and the acceleration and deceleration of the horizontal movement. The model then is trained and tested on two flight patterns to simulate a surveillance application of a UAV, and can predict with 98.773% mean of energy accuracy of the missions which are started from the take off and ended with the return to the launch command. Moreover, the trained and tested regression model is used to be the cost function of an optimal path planning scheme, which is designed from a clustered 3D real pilot flight pattern with the proposed k-agglomerative clustering method, and is processed via A-star and set-based particle-swarm-optimization (S-PSO) algorithm with adaptive weights. In addition, an online adaptive neural network (ANN) controller with varied learning rates is then designed and tested in this thesis to ensure the control stability while having a reliably fast disturbance rejection response. The effectiveness of the proposed framework is verified by numerical simulations and experimental results. By applying the proposed optimal path planning scheme, the energy consumption of the optimal path is only 72.3397 Wh while the average consumed energy of real pilot flight data is 96.593Wh. Moreover, the proposed ANN control improves average root-mean-square error (RMSE) of horizontal and vertical tracking performance by 49.083% and 37.50% in comparison with a proportional-integral-differential (PID) control and a fuzzy control under the occurrence of external disturbances. According to all of the results, the combination of the proposed energy consumption prediction model, optimal path planning scheme, and ANN controller can achieve a complete energy-efficient UAV surveillance systems with fast disturbance rejection response.

[1] Z. Liu, R. Sengupta and A. Kurzhanskiy, “A power consumption model for multi-rotor small unmanned aircraft systems,” in International Conference on Unmanned Aircraft Systems (ICUAS), pp. 310-315, 2017.
[2] N. Bezzo, K. Mohta, C. Nowzari, I. Lee, V. Kumar and G. Pappas, “Online planning for energy-efficient and disturbance-aware uav operations,” in International Conference on Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ, pp. 5027-5033, 2016.
[3] A. Abdilla, A. Richards and S. Burrow, “Power and endurance modelling of battery-powered rotorcraft,” in 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 675-680, 2015.
[4] M. Valenti, B. Bethke, J. P. How, D. P. De Farias and J. Vian, “Embedding health management into mission tasking for UAV teams,” in American Control Conference, 2007. ACC'07, pp. 5777-5783, 2007.
[5] K. Maekawa, S. Negoro, I. Taniguchi and H. Tomiyama, “Power measurement and modeling of quadcopters on horizontal flight,” in 2017 Fifth International Symposium on Computing and Networking (CANDAR), pp. 326-329, 2017.
[6] C.-M. Tseng, C.-K. Chau, K. Elbassioni, and M. Khonji. (2017). ‘‘Autonomous recharging and flight mission planning for battery operated autonomous drones.’’ [Online]. Available: https://arxiv.org/ abs/1703.10049
[7] T. Dietrich, S. Krug and A. Zimmermann, “An empirical study on generic multicopter energy consumption profiles,” in Systems Conference (SysCon), 2017 Annual IEEE International, pp. 1-6, 2017.
[8] H. V. Abeywickrama, B. A. Jayawickrama, Y. He and E. Dutkiewicz, “Comprehensive energy consumption model for unmanned aerial vehicles, based on empirical studies of battery performance,” IEEE Access, vol. 6, pp. 58383-58394, 2018.
[9] M. Dorigo and M. Birattari, “Ant colony optimization,” Springer US, 2010.
[10] D. L. Applegate, R. E. Bixby, V. Chvatal and W. J. Cook. (March. 1, 2015). Concorde TSP Solver. Traveling Salesman Problem, [Online]. Available: www.math.uwaterloo.ca/tsp/concorde.
[11] S. S. Juneja, P. Saraswat, K. Singh, J. Sharma, R. Majumdar and S. Chowdhary, “Travelling salesman problem optimization using genetic algorithm,” in 2019 Amity International Conference on Artificial Intelligence (AICAI), pp. 264-268, 2019.
[12] S. K. Hadia, A. H. Joshi, C. K. Patel and Y. P. Kosta, “Solving city routing issue with particle swarm optimization,” International Journal of Computer Applications, vol. 47, pp. 27-30, 2012.
[13] W.-N. Chen, J. Zhang, H. S. H. Chung, W.-L. Zhong, W.-G. Wu and Y.-H. Shi, “A novel set-based particle swarm optimization method for discrete optimization problems,” IEEE Transactions on Evolutionary Computation, vol. 14, pp. 278-300, 2009.
[14] Y. Weng, W.-N. Chen, A. Song and J. Zhang, “Set-based comprehensive learning particle swarm optimization for virtual machine placement problem,” in 2018 Ninth International Conference on Intelligent Control and Information Processing (ICICIP), pp. 243-250, 2018.
[15] L. Amorosi, L. Chiaraviglio and J. Galán-Jiménez, “Optimal energy management of UAV-based cellular networks powered by solar panels and batteries: formulation and solutions,” IEEE Access, vol. 7, pp. 53698-53717, 2019.
[16] C.-W. Lim, S. Park, C.-K. Ryoo, K. Choi and J.-H. Cho, “A path planning algorithm for surveillance UAVs with timing mission constrains,” in International Conference on Control, Automation, and Systems (ICCAS), pp. 2371-2375, 2010.
[17] K. Dorling, J. Heinrichs, G. G. Messier and S. Magierowski, “Vehicle routing problems for drone delivery,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 47, pp. 70-85, 2016.
[18] J. Kwak and Y. Sung, “Autonomous UAV flight control for GPS-based navigation,” IEEE Access, vol. 6, pp. 37947-37955, 2018.
[19] T. Jiang, D. Lin and T. Song, “Finite-time backstepping control for quadrotors with disturbances and input constraints,” IEEE Access, vol. 6, pp. 62037-62049, 2018.
[20] S. Busarakum and V. Srichatrapimuk, “The design of sliding mode control of a hexarotor,” in 2014 IEEE Conference on Systems, Process and Control (ICSPC), pp. 47-52, 2014.
[21] M. Walid, N. Slaheddine, A. Mohamed and B. Lamjed, “Modeling and control of a quadrotor UAV,” in 2014 15th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA), pp. 343-348, 2014.
[22] M. Moussid, A. Sayouti and H. Medromi, “Dynamic modeling and control of a hexarotor using linear and nonlinear methods,” International Journal of Applied Information Systems, vol. 9, pp. 9-17, 2015.
[23] F. Fakurian, M. B. Menhaj and A. Mohammadi, “Design of a fuzzy controller by minimum controlling inputs for a quadrotor,” in 2014 Second RSI/ISM International Conference on Robotics and Mechatronics (ICRoM), pp. 619-624, 2014.
[24] F.-J. Lin, W.-J. Hwang and R.-J. Wai, “Ultrasonic motor servo-drive with online trained neural-network model-following controller,” IEE Proceedings-Electric Power Applications, vol. 145, pp. 105-110, 1998.
[25] F.-J. Lin and R.-J. Wai, “Hybrid controller using a neural network for a PM synchronous servo-motor drive,” IEE Proceedings-Electric Power Applications, vol. 145, pp. 223-230, 1998.
[26] R.-J. Wai, M.-W. Chen and Y.-K. Liu, “Design of adaptive control and fuzzy neural network control for single-stage boost inverter,” IEEE Transactions on Industrial Electronics, vol. 62, pp. 5434-5445, 2015.
[27] U. S. Ananthakrishnan, N. Akshay, G. Manikutty and R. R. Bhavani, “Control of quadrotors using neural networks for precise landing maneuvers,” in Artificial Intelligence and Evolutionary Computations in Engineering Systems, Springer, 2017, pp. 103-113.
[28] S. Jin, J. Zhang, L. Shen and T. Li, “On-board vision autonomous landing techniques for quadrotor: a survey,” in 2016 35th Chinese Control Conference (CCC), pp. 10284-10289, 2016.
[29] H. Liu, D. Derawi, J. Kim, and Y. Zhong, “Robust optimal attitude control of hexarotor robotic vehicles,” Nonlinear Dynamics, vol. 74, pp.1155-1168, 2013.
[30] S. Rajappa, M. Ryll, H.H. Bülthoff, and A. Franchi , “Modeling, control and design optimization for a fully-actuated hexarotor aerial vehicle with tilted propellers,” in 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 4006-4013, 2015.
[31] RD 100 Conference. (2018). RD 100 Conference, award winners finalists. [Online]. Available: https://www.rd100conference.com/awards/winners-finalists/year/2018/
[32] Y. Chen, H. Zhang, and M. Xu, “The coverage problem in UAV network: A survey,” in Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT). pp. 1-5m 2014.
[33] Y. Zeng and R. Zhang, “Energy-efficient UAV communication with trajectory optimization,” IEEE Transactions on Wireless Communications 16, vol. 6. pp. 3747-3760, 2017.
[34] A. Puri, “A survey of unmanned aerial vehicles (UAV) for traffic surveillance,” Department of Computer Science and Engineering, University of South Florida. pp. 1-29, 2005.
[35] ArduPilot Dev Team. (2016). Ardu Copter, copter home. [Online]. Available: http://ardupilot.org/copter/
[36] ArduPilot Dev Team. (2016). Mission Planner, mission planner home. [Online]. Available: http://ardupilot.org/planner/index.html
[37] W. McKinney, “ Data structures for statistical computing in python,” in Proceedings of the 9th Python in Science Conference , vol. 445, pp. 51-56, 2010 .
[38] H. Zou and T. Hastie, “Regularization and variable selection via the elastic net,” Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol. 67, pp. 301-320, 2005.
[39] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot and E. Duchesnay, “Scikit-learn: machine learning in python,” Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011.
[40] K. Kanistras, G. Martins, M. J. Rutherford, and K. P. Valavanis, “Survey of unmanned aerial vehicles (UAVs) for traffic monitoring,” Handbook of Unmanned Aerial Vehicles. pp. 2643-2666, 2015.
[41] Google, “Google OR-tools,”, (2019). [Online]. Available: https://developers.google.com/optimization/.
[42] R. K. Arakaki and F. L. Usberti, “An efficiency-based path-scanning heuristic for the capacitated arc routing problem,” Computers & Operations Research 103. pp. 288-395, 2019.
[43] F. Duchoň, A. Babinec, M. Kajan, P. Beňo, M. Florek, T. Fico and L. Jurišica, “Path planning with modified a star algorithm for a mobile robot,” Procedia Engineering, vol. 96, pp. 59-69, 2014.
[44] A. Pfrunder, A. P. Schoellig, and T. D. D. Barfoot, ‘‘A proof-of-concept demonstration of visual teach and repeat on a quadrocopter using an altitude sensor and a monocular camera,’’ in 2014 Canadian Conference on Computer and Robot Vision, pp. 238–245, 2014.
[45] M. Y. Arafat and S. Moh, “A survey on cluster-based routing protocols for unmanned aerial vehicle networks,” IEEE Access, vol. 7, pp. 498-516, 2018.
[46] J. Kwak, J. H. Park, and Y. Sung, “Emerging ICT UAV applications and services: Design of surveillance UAVs,” in International Journal of Communication Systems, pp. 1-10, 2019.
[47] L. Rokach and O. Maimon, “Clustering Methods,” in Data Mining and Knowledge Discovery Handbook, O. Maimon and L. Rokach, Eds., Boston, MA: Springer US, 2005, pp. 321-352.
[48] V. Satopaa, J. Albrecht, D. Irwin and B. Raghavan, “Finding a” kneedle” in a haystack: Detecting knee points in system behavior,” in 2011 31st International Conference on Distributed Computing Systems Workshops, pp. 166-171, 2011.
[49] J. Li, “Agglomerative connectivity constrained clustering for image segmentation,” Statistical Analysis and Data Mining: The ASA Data Science Journal, vol. 4, pp. 84-99, 2011.
[50] H. Sharma, A. Alekseychuk, P. Leskovsky, O. Hellwich, R.S. Anand, N. Zerbe, and P. Hufnagl, “Determining similarity in histological images using graph-theoretic description and matching methods for content-based image retrieval in medical diagnostics,” Diagnostic Pathology, vol. 7, no 1, pp. 134-154, 2012.
[51] ArduPilot Dev Team. (2019). SITL simulator (software in the loop). [Online]. Available: http://ardupilot.org/dev/docs/sitl-simulator-software-in-the-loop.html.
[52] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, pp. 1735-1780, 1997.
[53] J.C., Bansal, P.K. Singh, M. Saraswat, A. Verma, S.S Jadon,. And A. Abraham, “Inertia weight strategies in particle swarm optimization,” IEEE Third World Congress on Nature and Biologically Inspired Computing, pp. 633-640, 2011