本論文以設計一台自主電動車的機電系統為目的，製作一電動車。此一電動車之機電系統可分為兩部分：電動車之機構設計與自動駕駛系統。機構設計分為前輪轉向模組、後輪動力輸出模組、動力方向盤模組以及車輛懸吊模組四部分。其中，前輪轉向模組採用各自獨立馬達推動前輪轉向；後輪動力輸出模組，則是透過兩顆馬達個別輸出方式達到差速控制；另外為了能夠偵測路況資訊以及自動導航，在車輛上裝設兩部攝影機、四個車用雷達以及GPS感測器。於自動駕駛系統，包含一個使用者操作介面、路況偵測以及車輛控制。其中，使用者操作介面主要用於路徑規劃與自動駕駛導航，透過GPS資訊以及車道資訊做為導航定位基礎，並結合預先建立好之地圖資訊以A*搜尋演算法規劃行車路線。在路況偵測上，車輛在行駛過程中應用裝設之攝影機來獲取電動車前方影像資訊，並透過邊緣檢測分辨出車道，而另一攝影機的影像則搭配You Only Look Once第三版的神經網絡模型，偵測行車路線上是否出現行人。最後則整合上述資訊做為控制車輛運行之依據。於系統實際測試項目，主要設計一輛電動車，其整體尺寸大小為長3.7公尺、寬1.55公尺、高1.85公尺以及迴轉半徑為4公尺。為了進一步驗證所設計系統之可行性，將電動車實際運行於校園中。此系統透過設定起始地與目的地，並自主規劃出一條行進路徑。此外，在行駛過程中若行人出現於路線上，將會減速或停止並且發出語音提醒。經過驗證，本自主電動車根據美國汽車工程師協會(SAE)之定義，屬於Level 3，即在一定條件下可以監控路面情況，且車輛可以完成部分駕駛任務。

In this thesis, an autonomous electric vehicle with electrical and mechanical system is designed. This system can be separated into two parts, one is for the design of the electric vehicle and the other is for the autopilot system. First of all, the mechanical design includes the front wheel steering module, the rear wheel power module, the power steering module, and the vehicle suspension module. In the front wheel steering module, we use two individual motors to control the direction of two front tires. In the rear wheel power module, two power motors have two different rotating speed instead of using differential. In order to get the traffic information and the automatic navigation, two cameras, four avoidance radars, and GPS sensor are integrated in the vehicle’s.Second, the autopilot system includes the path planning, the automatic navigation, the lane detection, and the pedestrian detection. Global Position System(GPS) and the lane’s information are integrated in the path planning and the automatic navigation. Then we combine the pre-established information of the map and use A* algorithm to plan the route. Additionally, this vehicle can use cameras to get the information in front of the vehicle while it is moving. And through the edge detection, this vehicle can distinguish the lane. The other camera imports the neural network You Only Look Once(YOLO)v3 to detect the pedestrians on the lane. In the experiment, a vehicle was built which size is 3.7 meter in length, 1.55 meter in width, 1.85 meter in height, and the radius of gyration is 4 meter. To verify the vehicle’s feasibility, we let the vehicle move in the campus. The route is planned automatically through setting the starting point and destination in the system. Besides, if there are pedestrians on the lane of the route, it would get slowly or stop with reminding sound. According to Society of Automotive Engineers(SAE), this system is classified in level3 which can move automatically in uncomplicated environment.

[1] Q. Li, L. Chen, M. Li, S. L. Shaw and A. Nüchter, “A Sensor-Fusion Drivable-Region and Lane-Detection System for Autonomous Vehicle Navigation in Challenging Road Scenarios,” IEEE Transactions on Vehicular Technology, vol. 63, issue. 2, pp. 540–555, 2014.
[2] R. Gopalan, T. Hong, M. Shneier, and R. Chellappa, “A learning approach towards detection and tracking of lane markings,” IEEE Transactions on Intelligent Transportation Systems, vol. 13, issue. 3, pp. 1088–1098, 2012.
[3] C. Guo, S. Mita, and D. McAllester, “Robust road detection and tracking in challenging scenarios based on Markov random fields with unsupervised learning,” IEEE Transactions on Intelligent Transportation Systems, vol. 13, issue. 3, pp. 1338– 1354, 2012.
[4] J. Álvarez and A. Lopez, “Road detection based on illuminant invariance,” IEEE Transactions on Intelligent Transportation Systems, vol. 12, issue. 1, pp. 184–193, 2011.
[5] H. Cheng, C. Yu, C. Tseng, K. Fan, J. Hwang, and B. Jeng, “Environment classification and hierarchical lane detection for structured and unstructured roads,” IET Computer Vision, vol. 4, issue. 1, pp. 37–49, 2010
[6] O. Kaiwartya, Y. Cao, J. Lloret, S. Kumar, N. Aslam, R. Kharel, A. H. Abdullah, R. R. Shah, “Geometry-based Localization for GPS Outage in Vehicular Cyber Physical Systems,” IEEE Transactions on Vehicular Technology, vol. 67, issue. 5, pp. 3800–3812, 2018.

[7] K. Sundar, S. Misra and S. Rathinam, “Routing unmanned vehicles in GPS-denied environments,” IEEE International Conference on International Conference on Unmanned Aircraft Systems , pp. 4579–4591, 2017.
[8] D. Cui, J. Xue and N. Zheng, “Real-Time Global Localization of Robotic Cars in Lane Level via Lane Marking Detection and Shape Registration,” IEEE Transactions on Intelligent Transportation Systems, vol. 17, issue. 4, pp. 1039–1050, 2016.
[9] K. Jo, Y. Jo and J. K. Suhr, “Precise Localization of an Autonomous Car Based on Probabilistic Noise Models of Road Surface Marker Features Using Multiple Cameras,” IEEE Transactions on Intelligent Transportation Systems, vol. 16, issue. 6, pp. 3377–3392, 2015.
[10] Y. Gu, Y. Wada, L. Hsu and S. Kamijo, “Vehicle self-localization in urban canyon using 3D map based GPS positioning and vehicle sensors,” IEEE Conferences on Connected Vehicles and Expo , pp. 792–798, 2014.
[11] J. Courbon, Y. Mezouar and P. Martinet, “Autonomous Navigation of Vehicles from a Visual Memory Using a Generic Camera Model,” IEEE Transactions on Intelligent Transportation Systems, vol. 10, issue. 3, pp. 392–402, 2009.
[12] N. Morales, J. Toledo, L. Acosta and J. S. Medina, “A Combined Voxel and Particle Filter-Based Approach for Fast Obstacle Detection and Tracking in Automotive Applications,” IEEE Transactions on Intelligent Transportation Systems, vol. 18, issue. 7, pp. 1824–1834, 2017.
[13] V. D. Nguyen, H. V. Nguyen, D. T. Tran, S. J. Lee and J. W. Jeon, “Learning Framework for Robust Obstacle Detection, Recognition, and Tracking,” IEEE Transactions on Intelligent Transportation Systems, vol. 18, issue. 7, pp. 1633–1646, 2017.
[14] Y. Huang and S. Liu, “Multi-class obstacle detection and classification using stereovision and improved active contour models,” IET Intelligent Transport Systems, vol. 10, issue. 3, pp. 197–205, 2016.
[15] J. H. Aceituno, R. Arnay, J. Toledo and L. Acosta, “Using Kinect on an Autonomous Vehicle for Outdoors Obstacle Detection,” IEEE Sensors Journal, vol. 16, issue. 10, pp. 3603–3610, 2016.
[16] Z. Zhang, H. Xu, Z. Chao, X. Li and C. Wang, “A Novel Vehicle Reversing Speed Control Based on Obstacle Detection and Sparse Representation,” IEEE Transactions on Intelligent Transportation Systems, vol. 16, issue. 3, pp. 1321–1334, 2015.
[17] J. Han, D. Kim, M. Lee and M. Sunwoo, “Enhanced Road Boundary and Obstacle Detection Using a Downward-Looking LIDAR Sensor,” IEEE Transactions on Vehicular Technology, vol. 61, issue. 3, pp. 971–985, 2012.
[18] I. Chabini and S. Lan, “Adaptations of the A* algorithm for the Computation of Fastest Paths in Deterministic Discrete-Time Dynamic Networks,” IEEE Transactions on Intelligent Transportation Systems, vol. 3, no. 1, pp. 60–74, 2002.
[19] 張傑，「以改良的A*演算法規劃較佳導引路徑之研究」，碩士學位論文，大同大學，民國98年。
[20] 張書豪，「具自主導航與避障之嵌入式移動機器人控制系統開發」，碩士學位論文，國立臺灣科技大學，民國99年。