近年來，為了提升人們交通行駛上的安全性，因此智慧型車輛蓬勃發展。而為了使智慧型車輛發揮出更好的工作效益，所以識別駕駛人意圖的研究議題就被提出。本研究將尋找出能有效識別出駕駛人車道變換意圖之推論，故將探討不同的資訊源和方法的比對。首先，設計出不同的實驗情境假設，並透過駕駛模擬器收集駕駛人Lane Change (LC) 和 Lane Keeping (LK) 的駕駛行為資訊。再將收集好的資訊源經過資料處理後，建立成訓練資料庫以及驗證資料庫兩部分。然後，利用此資料庫進行支持向量機 (Support Vector Machine, SVM) 與動態貝氏網路 (Dynamic Bayesian Network, DBN) 的模型訓練和驗證比對。除此之外，使用灰關聯分析 (Grey Relation Analysis) 各資訊源與駕駛意圖之間的關聯性。實驗結果顯示，使用支持向量機搭配方向盤角度、偏航角、偏航角速率以及側向位移做為資訊源，將能有效識別出駕駛人車道變換意圖。

In recent years, in order to enhance the safety of traffic, intelligent vehicles flourish. To make intelligent vehicles work effectively, driver intention recognition methods have been proposed recently. This study can effectively identify the driver of lane change intention, it explore the different information sources and methods. First, design the different experimental conditions assumed, and through the driving simulator to collect Lane Change (LC) and Lane Keeping (LK) data. Then collect source of information after data processing, created as a part of the training database and the validation database. Then use this database for training and validation of Support Vector Machine (SVM) and Dynamic Bayesian Network (DBN) model. In addition, the relationship between the information sources and the driving intention is analyzed. The experimental results show that SVM with steering wheel angle, yaw angle, yaw rate, and lateral displacement as a source of information, we can effectively identify the driver lane change intention.

[1]. Woodson, W. E., and Conover, D. W., Human engineering guide for equipment designers, 2nd ed., California：University of California Press, 1970.
[2]. 蘇威丞, “駕駛人操控介入意圖推論之研究,” 國立臺灣科技大學機械工程系碩士論文, 台灣 台北, 2010.
[3]. Liu, L., Xu, G., and Song, Z., “Driver lang changing behavior analysis based on parallel bayesian networks,” Natural Computation (ICNC), 2010 Sixth International Conference on, Yantai, Shandong, Vol. 3, Aug. 2010, pp.1232-1237.
[4]. Xu, G., Liu, L., and Song, Z., “Driver behavior analysis based on bayesian network and multiple classifiers,” Intelligent Computing and Intelligent System (ICIS), 2010 IEEE International Conference on, Vol. 3, Oct. 2010, pp. 663-668.
[5]. Liu, A. and Pentland, A., “Towards real-time recognition of driver intentions,” Intelligent Transportation System, 1997. ITSC ’97., IEEE Conference on, Boston, MA, USA, Nov. 1997, pp. 236-241.
[6]. Zong, C.F., Yang, X., Wang, C., and Zhang, G.C., “Driving intentions identification and behaviors prediction in car lane change,” Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), Vol. 39, NO. 1, March 2009, pp. 27-32.
[7]. Hou, H., Jin, L., Niu, Q., Sun, Y., and Lu, M., “Driver intention recognition method using continuous hidden markov model,” International Journal of Computational Intelligence Systems, Vol. 4, NO. 3, May 2011, pp. 386-393.
[8]. Raksincharoensak, P., Mizushima, T., and Nagai, M., “Direct yaw moment control system based on driver behaviour recognition,” 20th Symposium of the International Association for Vehicle System Dynamics, IAVSD, Vol. 46, 2008, pp. 911-921.
[9]. Yuhara, N. and Tajima, J., “Advanced steering system adaptable to lateral control task and driver's intention,” Vehicle System Dynamics, Vol. 36, NO. 2-3, Sept. 2001, pp. 119-158.
[10]. Tezuka, S., Soma, H., and Tanifuji, K., “A study of driver behavior inference model at time of lane change using bayesian networks,” Industrial Technology, 2006. ICIT 2006. IEEE International Conference on, Dec. 2006, pp. 2308-2313.
[11]. Berndt, H. and Dietmayer, K., “Driver intention inference with vehicle onboard sensors,” Vehicular Electronics and Safety (ICVES), 2009 IEEE Internation Conference on, Nov. 2009, pp. 102-107.
[12]. McCall, J.C. and Trivedi, M.M., “Driver behavior and situation aware brake assistance for intelligent vehicles,” Proceedings of the IEEE, Vol. 95, NO. 2, Feb. 2007, pp. 374-387.
[13]. McCall, J.C., Trivedi, M.M., Wipf, D., Bhaskar, R., “Lane change intent analysis using robust operators and sparse bayesian learning,” IEEE Trans. Intelligent Transportation Systems, Vol. 8, NO. 3, Sept. 2007, pp. 431-440.
[14]. Doshi, A. and Trivedi, M.M., “A comparative exploration of eye gaze and head motion cues for lane change intent prediction,” Intelligent Vehicles Symposium, 2008 IEEE, June 2008, pp. 49-54.
[15]. Doshi, A. and Trivedi, M.M., “Investigating the relationships between gaze patterns, dynamic vehicle surround analysis, and driver intentions,” Intelligent Vehicles Symposium, 2009 IEEE, June 2009, pp. 887-892.
[16]. Doshi, A. and Trivedi, M.M., “On the roles of eye gaze and head dynamics in predicting driver’s intent to change lanes,” Intelligent Transportation Systems, IEEE Transactions on, Vol. 10, NO. 3, Sept. 2009, pp. 453-462.
[17]. Doshi, A., Morris, B.T., and Trivedi, M.M., “On-road prediction of driver's intent with multimodal sensory cues,” Pervasive Computing, IEEE, Vol. 10, NO. 3, March 2011, pp. 22-34.
[18]. Morris, B.T., Doshi, A., Trivedi, M.M., “Lane change intent prediction for driver assistance: On-road design and evaluation,” Intelligent Vehicles Symposium (IV), 2011 IEEE, June 2011, pp. 895-901.
[19]. Ikenishi, T., Kamada, T., and Nagai, M., “Classification of driver steering intention at the vehicle running based on brain-computer interface using electroencephalogram,” Japan Society of Mechanical Engineers, Shinanomachi 35, Shinjuku-ku, Tokyo, 160-0016, Japan, Vol. 74, NO. 5, May 2008, pp. 1347-1354.
[20]. Itoh, M., Yoshimura, K., and Inagaki, T., “Inference of large truck driver’s intent to change lanes to pass a lead vehicle via analyses of driver’s eye glance behavior in the real world,” SICE, 2007 Annual Conference, Sept. 2007, pp. 2385-2389.
[21]. Sezgin, T.M., Davies, I., and Robinson, P., “Multimodal inference for driver-vehicle interaction,” International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interfaces, ICMI-MLMI'09, Nov. 2009, pp. 193-197.
[22]. Schubert, R., Schulze, K., and Wanielik, G., “Situation assessment for automatic lane-change maneuvers,” Intelligent Transportation Systems, IEEE Transactions on, Vol. 11, NO. 3, Sept. 2010, pp. 607-616.
[23]. Lefevre, S., Laugier, C., and Ibanez-Guzman, J., “Exploiting map information for driver intention estimation at road intersections,” Intelligent Vehicles Symposium (IV), 2011 IEEE, June 2011, pp. 583-588.
[24]. Mabuchi, R. and Yamada, K., “Study on driver-intent estimation at yellow traffic signal by using driving simulator,” Intelligent Vehicles Symposium (IV), 2011 IEEE, June 2011, pp. 95-100.
[25]. Lidstrom, K. and Larsson, T., “Model-based estimation of driver intentions using particle filtering,” Intelligent Transportation Systems, 2008. ITSC2008. 11th International IEEE Conference on, Oct. 2008, pp. 1177-1182.
[26]. Johansson, B. and Gafvert, M., “Untripped SUV rollover detection and prevention,” IEEE Conference on Decision and Control (CDC), Atlantis, Paradise Island, Bahamas, 2004, pp. 5461-5466.
[27]. Paul, J. Th., “Reference manual for a lane keeping simulation tool,” The University of Michigan Transportation Research Institute, July 1995.
[28]. 楊釧暉, “結合駕駛人資訊之車道維持輔助控制器設計,” 國立臺灣科技大學機械工程系碩士論文, 台灣 台北, 2009.
[29]. Vapnik, V. N., “The nature of statistical learning theory,” Springer-Verlag, 1995.
[30]. Boser, B. E., Guyon, I. M., and Vapnik, V. N., “A training algorithm for optimal margin classifiers,” Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory, Pittsburgh, PA, 1992, pp. 144-152.
[31]. http://www.cmlab.csie.ntu.edu.tw/~cyy/learning /tutorials/SVM2.pdf
[32]. 黃再源, “使用啟始分群分類法進行垃圾郵件過濾的研究,” 逢甲大學資訊電機工程碩士在職專班碩士論文, 台灣 台中, 2008.
[33]. 蕭仁惠, “利用階層式支持向量機演算法建立應用於行動化視覺搜尋之影像字彙樹,” 國立交通大學資訊學院碩士在職專班資訊組碩士論文, 台灣 新竹, 2009.
[34]. 連毅樫, “適應駕駛人之車道偏離警示系統,” 國立臺灣科技大學機械工程系碩士論文, 台灣 台北, 2008.
[35]. 李宜勳, “整合異質性資料以預測基因網路,” 國立成功大學資訊管理研究所碩士論文, 台灣 台南, 2004.
[36]. 吳維鈞, “以多模塊集成式貝氏網路建立智慧型家庭個人化服務,” 國立中正大學資訊工程所碩士論文, 台灣 嘉義, 2007.
[37]. 潘家琳, “利用動態貝氏網路分析基因網路的調控,” 慈濟大學醫學資訊研究所碩士論文, 台灣 花蓮, 2005.
[38]. Murphy. K., “Dynamic bayesian networks: Representation, inference and Learning,” Phd Thesis. UC Berkeley, Computer Science Division, July 2002.
[39]. 顧正偉, “利用多觀察值型馬可夫模型進行人體動作辨識,” 國立交通大學資訊工程系所碩士論文, 台灣 新竹, 2004.
[40]. MacQueen, J.B., “Some methods for classification and analysis of multivariate observations,” Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, University of California Press, 1967, pp. 281-297.
[41]. Chang, C.C. and Lin, C.J., “LIBSVM: A library for support vector machines,” Department of Computer Science National Taiwan University, Taipei Taiwan, 2001.
[42]. Murphy, K.P., “The bayes net toolbox for matlab,” Department of Computer Science University of California, Berkeley, CA, Oct. 2001.
[43]. 鄧聚龍, 《灰色預測與決策》, 華中理工大學出版社, 1986.