請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/49742
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 許添本(Tien-Pen Hsu) | |
dc.contributor.author | Ting-You Lin | en |
dc.contributor.author | 林亭佑 | zh_TW |
dc.date.accessioned | 2021-06-15T11:45:27Z | - |
dc.date.available | 2023-08-18 | |
dc.date.copyright | 2020-08-24 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020-08-12 | |
dc.identifier.citation | [1] 陳建青. 先進駕駛輔助系統幕後功臣,車用影像辨識技術 [Online] Available: https://www.artc.org.tw/chinese/03_service/03_02detail.aspx?pid=2809 [2] 'Support - Autopilot.' Tesla. https://web.archive.org/web/20190410153216/https://www.tesla.com/support/autopilot (accessed 6 Sep., 2019). [3] 無人載具科技創新實驗管理辦法, 民國108年06月06日. [4] 無人載具科技創新實驗條例, 民國107年12月19日. [5] D. Yeh, '1天訓練=100年道路測試!Waymo自駕車是這樣模仿人類開車,' 陳映璇, Ed., ed. Taiwan: 數位時代 Business Next, 2020, https://edm.bnext.com.tw/saleskit/contactbn.htm. [6] 機動車輛數簡易資料查詢網頁 [Online] Available: https://stat.motc.gov.tw/mocdb/stmain.jsp?sys=100 funid=a3301 [7] F. A. M. Babu, P. Vortisch, and T. V. Mathew, 'Modelling of motorcycle movements in mixed traffic conditions,' in 94th Annual Meeting Transportation Research Board, Washington, DC, 2014. [8] D. N. HUYNH, M. Boltze, and A. T. VU, 'Modelling mixed traffic flow at signalized intersectionusing social force model,' Journal of the Eastern Asia Society for Transportation Studies, vol. 10, pp. 1734-1749, 2013. [9] L. X. Nguyen, S. Hanaoka, and T. Kawasaki, 'Describing Non–Lane-Based Motorcycle Movements in Motorcycle-Only Traffic Flow,' Transportation research record, vol. 2281, no. 1, pp. 76-82, 2012. [10] G. Di Gennaro, A. Buonanno, A. Di Girolamo, and F. A. Palmieri, 'Intent Classification in Question-Answering Using LSTM Architectures,' arXiv preprint arXiv:2001.09330, 2020. [11] S. Cohan, 'Team LSTM: player trajectory prediction in basketball games using graph-based LSTM networks,' University of British Columbia, 2020. [12] K. Nagel and M. Schreckenberg, 'A cellular automaton model for freeway traffic,' Journal de physique I, vol. 2, no. 12, pp. 2221-2229, 1992. [13] A. D. May, Traffic flow fundamentals. 1990. [14] G. Willmann, 'Zustandsformen des Verkehrsablaufs auf Autobahnen,' SCHRIFTENR INST VERKEHRSWES UNIV KARLSRUHE 19, no. 19, 1978. [15] U. Sparmann, 'Spurwechselvorgänge auf zweispurigen BAB-Richtungsfahrbahnen,' FORSCH STRASSENBAU U STRASSENVERKEHRSTECH 263, no. 263, 1978. [16] R. Wiedemann, 'Simulation des Strassenverkehrsflusses,' 1974. [17] D. N. Dailisan and M. T. Lim, 'Agent-based modeling of lane discipline in heterogeneous traffic,' Physica A: Statistical Mechanics and its Applications, vol. 457, pp. 138-147, 2016. [18] 張太乙, '基於車輛運動學之機車路段微觀車流模型,' 臺灣大學土木工程學研究所學位論文, pp. 1-79, 2019. [19] M. Zhou, X. Qu, and X. Li, 'A recurrent neural network based microscopic car following model to predict traffic oscillation,' Transportation research part C: emerging technologies, vol. 84, pp. 245-264, 2017. [20] S. H. Park, B. Kim, C. M. Kang, C. C. Chung, and J. W. Choi, 'Sequence-to-sequence prediction of vehicle trajectory via LSTM encoder-decoder architecture,' in 2018 IEEE Intelligent Vehicles Symposium (IV), 2018: IEEE, pp. 1672-1678. [21] 吳建霆, '以深度學習長短時記憶神經網路演算法建立混合車道之機車行為模式,' 淡江大學運輸管理學系運輸科學碩士班學位論文, pp. 1-93, 2018. [22] A. Kuefler, J. Morton, T. Wheeler, and M. Kochenderfer, 'Imitating driver behavior with generative adversarial networks,' in 2017 IEEE Intelligent Vehicles Symposium (IV), 2017: IEEE, pp. 204-211. [23] K. Messaoud, I. Yahiaoui, A. Verroust, and F. Nashashibi, 'Attention Based Vehicle Trajectory Prediction,' IEEE Transactions on Intelligent Vehicles, 2020. [24] I. Goodfellow et al., 'Generative adversarial nets,' in Advances in neural information processing systems, 2014, pp. 2672-2680. [25] 'Keras API Reference.' https://keras.io/api/ (accessed 2020). [26] 鄭允中, '基於長短期記憶遞迴類神經網路之新台幣兌美元匯率預測模型,' 2017. [27] S. Hochreiter and J. Schmidhuber, 'Long short-term memory,' Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997. [28] 謝秉勳, '地面目標物識別及相對定位視覺演算法,' 成功大學航空太空工程學系學位論文, pp. 1-68, 2018. [29] 'Open Source Computer Vision Library.' Intel. http://opencv.org/ (accessed. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/49742 | - |
dc.description.abstract | 機車的機動性能與駕駛者感知判斷之間的關係相當複雜,且行為模式與汽車有相當的差異,導致典型以跟車模式與變換車道模式為基礎的微觀車流模擬軟體應用於機車組成比例大的道路環境表現不佳。此外,機車行為與駕駛因素有很大的關聯,卻難以量化成數學模式,許多國內外文獻藉由神經網路探索出非結構化的模式,並藉由神經網路中複雜的結構,獲取影響機車行為更細微的特徵因素,以有效的表達道路上車輛行為及駕駛因素的特徵。 根據文獻證實,深度學習演算法能有效地將車輛周圍複雜的車輛間互動與影響駕駛行為的因素特徵化,而遞迴神經網路或是其他改良式網路等同一類型的模型,適合用於預測如車流行為等時間序列上的空間移動行為。本研究將基於這些文獻,提出以長短期記憶神經網路為基礎的機車微觀車流模式。模式架構中以局部主體機車與各角度的周圍相鄰車輛變數組成多個全連接層,提取時間維度上各時點主體車輛與周圍車輛微妙的互動關係,接著以長短期記憶層擬合這些關係隨時間序列變化的資訊,最後以駕駛決策的加速度與行進方向作為模式輸出,以描述機車的微觀行為。 本研究的資料來源為高雄智慧機車計畫案的空拍車流資料,將車流影像轉換為軌跡資料後,得以用於訓練及驗證本研究提出的模式。研究範圍為路段中推進的行為模式。微觀驗證顯示本研究之模式有能力重現諸如超車等機車特有行為,而巨觀驗證足以證明模式的可行性。本研究除了預期提出穩健的車流模擬模式,亦提供針對在不同地點以神經網路為基礎的建模流程。 | zh_TW |
dc.description.abstract | The relationship between the maneuverability of scooters and the driver's perception is quite complicated, and the behavior pattern is quite different from that of the car, which led to the poor performance of the typical microscopic traffic simulation software based on the car-following model and lane-changing model when applied to roads with a large proportion of scooters. In addition, scooter behavior is closely related to driver factors, but it is difficult to quantify it into a mathematical model. Many domestic and foreign literatures have used neural networks to explore unstructured patterns, and we can obtain more subtle characteristic factors that affect the behavior of the scooter to effectively express the characteristics of the vehicle behavior and driver factors on the road through the complex structure in the neural network. According to the literatures, the deep learning algorithm can effectively characterize the complex inter-vehicle interactions around the vehicle and the factors that affect driving behavior. The same type of model, such as recurrent neural networks or other improved networks, is suitable for predicting spatial movement behavior in time series such as driving behavior. Based on these literatures, this study will propose a microscopic traffic model based on long short-term memory neural networks. In the model architecture, multiple fully connected layers are composed of local subject scooter and neighboring vehicle variables at various angles to extract the subtle interaction relationship between subject scooter and surrounding vehicles at each time step in the time dimension. Then, the long short-term memory layers are used to fit the information of these relationships with the time series. Finally, the acceleration and driving direction of the driving decision are used as the model output to describe the microscopic behavior of the scooter. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T11:45:27Z (GMT). No. of bitstreams: 1 U0001-1208202000054800.pdf: 2259323 bytes, checksum: 43a2b1d2d561e6d62cf0335e7a5549a6 (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 摘要 ii Abstract iii 目錄 iv 圖目錄 vii 表目錄 viii 第1章 緒論 1 1.1 研究背景 1 1.2 研究目標 2 1.3 研究範圍 3 1.4 研究架構 3 第2章 文獻回顧 5 2.1 無車道概念微觀車流模式 (Non-Lane-Based Microscopic Traffic Flow Model) 5 2.1.1 社會力模式 Social Force Model 6 2.1.2 安全空間模式 Safety Space Based Model 10 2.1.3 整合模式 12 2.2 深度學習演算法應用於車流模式 16 2.2.1 遞迴神經網路 Recurrent Neural Network, RNN 18 2.2.2 長短期記憶神經網路 Long Short-term Memory, LSTM 18 2.2.3 其他常見演算法 20 2.3 小結 21 第3章 模式建構 23 3.1 遞迴神經網路 Recurrent Neural Network, RNN 23 3.2 長短期記憶神經網路 Long Short-term Memory, LSTM 25 3.2.1 LSTM單元結構 25 3.2.2 批次訓練、損失函數與最佳化演算法 Batch, Loss Function and Optimizer 27 3.2.3 時序倒傳遞法 Backpropagation Through Time, BPTT 28 3.3 基於LSTM的路段機車微觀模式 28 3.3.1 輸入變數 29 3.3.2 輸出變數 31 3.3.3 模式架構 31 3.3.4 損失函數 Loss Function 33 3.3.5 超參數 Hyperparameters 33 第4章 微觀車流資料調查 36 4.1 資料蒐集 36 4.1.1 調查目的及項目 36 4.1.2 調查方法 37 4.1.3 調查範圍選定 37 4.2 調查資料預處理 39 4.2.1 時空軌跡資料追蹤 39 4.2.2 空間座標轉換 41 4.2.3 計算周圍車輛與主體車輛相對關係變數 42 4.3 訓練資料集格式轉換 44 4.3.1 序列資料長度 44 4.3.2 輸入變數格式 45 4.3.3 輸出變數格式 45 第5章 模式訓練與驗證 46 5.1 模式訓練結果 46 5.2 微觀驗證 47 5.2.1 驗證指標 47 5.2.2 驗證結果與比較 48 5.3 巨觀驗證 49 5.3.1 驗證指標 49 5.3.2 驗證環境與結果 49 第6章 結論與建議 51 6.1 結論 51 6.2 建議 52 參考文獻 53 | |
dc.language.iso | zh-TW | |
dc.title | 基於LSTM神經網路之機車微觀車流模型 | zh_TW |
dc.title | Microscopic Traffic Flow Modeling for Motorcycles using Long Short-Term Memory Neural Network | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 胡大瀛(Ta-Yin Hu),邱裕鈞(Yu-Chiun Chiou) | |
dc.subject.keyword | 微觀車流模擬,混合車流,機車,長短期記憶神經網路,深度學習, | zh_TW |
dc.subject.keyword | microscopic traffic simulation,mix traffic flow,motorcycles,long short-term memory neural network,deep learning, | en |
dc.relation.page | 54 | |
dc.identifier.doi | 10.6342/NTU202003033 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2020-08-13 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
顯示於系所單位: | 土木工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-1208202000054800.pdf 目前未授權公開取用 | 2.21 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。