近年來，隨著道路上的車輛越來越多，交通事故發生的數量也逐年增加。 為了有效降低交通事故發生的機率，本篇論文提出了一種演算法，可以用來預測車輛未來軌跡以便及早提醒駕駛碰撞發生的可能性。在車輛路徑預測的研究中，大部分都利用昂貴的外接感測器，但考量成本問題在一般情況比較難以被實作。相反的，我們所提出的演算法會利用簡單又便宜的感測器如GPS或市面上常見的相機來收集資料。 此外我們的演算法也會利用從CAMP所得的車輛迴轉半徑來進行預測，從GPS 所得的經緯度可以用來定位以及預測車輛未來的所在位置，從相機收集到的資料可以用來判斷車輛是否會轉彎。再來我們也會考慮駕駛的反應時間來增進我們預測的準確度。最後實驗結果也顯示利用我們的演算法可以有效地降低預測位置與實際位置的誤差。

As more and more vehicles are on the road, the number of traffic accidents increases each year. To battle with the traffic accidents, one possible mean is to predict the future trajectory of the vehicle so that the driver can be informed when a possible collision is detected in advance. In this thesis, an algorithm for vehicle's future trajectory prediction is proposed. Although the similar research topic has been studied for many years, most of the existing solutions make use of expensive external sensors, which makes these solutions difficult to be adopted for the general public.
On the contrary, our proposed trajectory prediction algorithm collects data from simple and inexpensive sensors like GPS and off-the-shelf camera. The radius of the vehicle from CAMP is adopted in our vehicle path prediction algorithm. The GPS data, such as latitude and longitude, can be used to localize/predict the current/future position of the vehicle. The turn detection data obtained from camera is used to determine if the host vehicle is making a turn. The driver's reaction time is taken into account as a delay to improve the accuracy of the prediction. The experiment results indicate that the position deviation between the predicted position and the ground truth has been significantly reduced by using our algorithm.

[1] Iwcu 4.4 obu specication. https://www.itri.org.tw/chi/Content/MsgPic01/Contents.aspx?SiteID=1&MmmID=620624054325020775&MSid=
620634640463241437.
[2] National highway traffic safety administration. https://www.nhtsa.gov/.
[3] parkingdistance. http://www.freeway.gov.tw/Publish.aspx?cnid=516&p=2230.
[4] Toyota. http://www.toyota.com.tw/tech/safety_technology_parallax/
safety_technology_parallax/innovation/safety_technology/2016.aspx.
[5] volkswagen. http://www.volkswagen.com.tw/zh/models/the-new-tiguan/
highlights.suffix.html/selection=3.html#none.
[6] Jacob Benesty, Jingdong Chen, Yiteng Huang, and Israel Cohen. Mean Squared
Error Criterion. 2009.
[7] Kyongsu Yi Beomjun Kim. Probabilistic states prediction algorithm using multi-sensor fusion and application to smart cruise control systems. In Intelligent Vehicles Symposium (IV), 2013.
[8] Ulisses Braga-Neto. Particle ltering approach to state estimation in boolean dynamical systems. In Global Conference on Signal and Information Processing (GlobalSIP),2013.
[9] Derek Caveney. Numerical integration for future vehicle path prediction. In ACC,2007.44
[10] Derek Caveney. Stochastic path prediction using the unscented transform with numerical integration. In Intelligent Transportation Systems Conference, 2007.
[11] Derek Caveney. Hierarchical software architectures and vehicular path prediction for cooperative driving applications. In Intelligent Transportation Systems, 2008.
[12] Arijit Chowdhury, Tapas Chakravarty, and P.Balamuralidhar. Estimating true speed of moving vehicle using smartphone-based gps measurement. In Systems, Man and Cybernetics (SMC), pages 5{8, 2014.
[13] Deering, Richard, and K. Annual report of the crash avoidance metrics partnership.
In National Highway Traffic Safety Administration (NHTSA), 2002.
[14] Przemyslaw Dymarski. Hidden Markov Models, Theory and Applications. 2016.
[15] Ahmed El-Rabbany. Introduction to GPS: The Global Positioning System. 2002.
[16] R.A. Haddad and A.N. Akansu. A class of fast gaussian binomial lters for speech and image processing. In IEEE Transactions on Acoustics, Speech and Signal Processing,pages 723{727, 1991.
[17] Jihua Huang Han-Shue Tan. Dgps-based vehicle-to-vehicle cooperative collision warning: Engineering feasibility viewpoints. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 7:415{428, December 2006.
[18] Jihua Huang and Han Shue Tan. Vehicle future trajectory prediction with a dgps/insbased positioning system. In ACC, pages 111{120, 2006.
[19] Industrial Technology Research Institute (ITRI). Host vehicle path prediction (hvpp)reference design. In Intelligent Transportation system, 2011.45
[20] Wang Jingyu and Duan Jianmin. Lane detection algorithm using vanishing point.
In Machine Learning and Cybernetics (ICMLC), 2013, 2013.
[21] C.Galambos J.Matas and J.Kittler. Robust detection of lines using the progressive probabilistic hough transform. In Computer Vision and Image Understanding, pages 119{137, 2000.
[22] Kichun Jo, Minchul Lee, and Myoungho Sunwoo. Road slope aided vehicle position estimation system based on sensor fusion of gps and automotive onboard sensors.
In IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,volume 17, 2016.
[23] and Axelrad Kee, Parkinson. Wide area differential gps. In Navigation, Journal of the Institute of Navigation, 1991.
[24] Phil Kim. Kalman Filter for Beginners: with MATLAB Examples. 2011.
[25] Yukihiro Kubo, Tsuyoshi Kindo, Akihiko Ito, and Sueo Sugimoto. Dgps/ins/vvheelsensor integrationfor high accuracy land-vehicle positioning. In International
Technical Meeting of the Satellite Division of The Institute of Navigation (ION GPS1999), pages 555{564, 1999.
[26] Christian Laugier, Igor E. Paromtchik, Mao Yong, John-David Yoder, Christopher Tay, Kamel Mekhnacha, and Amaury Ngre. Probabilistic analysis of dynamic scenes
and collision risks assessment to improve driving safety. In IEEE Intelligent Transportation Systems Magazine, volume 3, pages 4{19, 2011.
[27] Xu Li and Qimin Xu. A reliable fusion positioning strategy for land vehicles in 46 gps-denied environments based on low-cost sensors. In IEEE TRANSACTIONS ON
INDUSTRIAL ELECTRONICS, volume 64, 2017.
[28] Wei Liu, XueZhiWen, Bobo Duan, Huai Yuan, and NanWang. Rear vehicle detection and tracking for lane change assist. In Intelligent Vehicles Symposium, 2007.
[29] Kamel Mekhnacha, Yong Mao, David Raulo, and Christian Laugier. The fast clustering-tracking algorithm in the bayesian occupancy lter framework. In Multi-
sensor Fusion and Integration for Intelligent Systems, 2008.
[30] Takahiro Wada Naoki Shibata, Seiji Sugiyama. Collision avoidance control with steering using velocity potential eld. In Intelligent Vehicles Symposium (IV), 2014.
[31] U.S. Government Printing Office. Collision Avoidance System Equipment and Compliance Deadlines. 1989.
[32] Alexander Verl Philipp Kohler, Christian Connette. Vehicle tracking using ultrasonic sensors and joined particle weighting. In IEEE International Conference on Robotics and Automation (ICRA), 2013.
[33] J.C. Reed. Side zone automotive radar criteria for target classication. In Intelligent Vehicles '95 Symposium., 2002.
[34] Martin Litschel Siegfried Dais, Dr. Uwe Kiencke. History of CAN technology. 1983.
[35] Bo Tang, Salman Khokhar, and Rakesh Gupta and. Turn prediction at generalized intersections. In Intelligent Vehicles Symposium (IV), 2015 IEEE, 2015.
[36] Lijo Thomas, Senju Thomas Panicker, Jerry Daniel J, and Tilty Tony. Dsrc based collision warning for vehicles at intersections. In ICACCS, 2016. 47
[37] Eric W Weisstein. Great circle. In MathWorld{A Wolfram Web Resource.
http://mathworld.wolfram.com/GreatCircle.html, 2002.
[38] Sathiamoorthy Manoharan Xiaowen Gong. On predicting vehicle tracks. In PacRim, 2011.
[39] Hao Xu, Hongchao Liu, Chin-Woo Tan, and Yuanlu Bao. Development and application of an enhanced kalman lter and global positioning system error-correction
approach for improved map-matching. In Journal of Intelligent Transportation Systems, 2010.4