跳到主要內容

臺灣博碩士論文加值系統

(18.97.14.82) 您好!臺灣時間:2025/02/19 10:26
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:顏傳宇
研究生(外文):YAN, CHUAN-YU
論文名稱:應用深度學習與專家系統於自動變換車道決策網路之設計
論文名稱(外文):Design of Decision Network for Automatic Lane Change using Deep Learning and Expert System
指導教授:陳柏全陳柏全引用關係
指導教授(外文):CHEN, BO-CHIUAN
口試委員:陳正夫蔣欣翰陳柏全
口試委員(外文):CHEN, ZHENG-FUCHIANG, HSIN-HANCHEN, BO-CHIUAN
口試日期:2022-07-22
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:車輛工程系
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:中文
論文頁數:97
中文關鍵詞:自動變換車道決策網路卷積神經網路長短期記憶網路深度學習專家系統風險評估
外文關鍵詞:automatic lane changedecision-making networkconvolutional neural networklong short-term memorydeep learningexpert systemrisk assessment
相關次數:
  • 被引用被引用:0
  • 點閱點閱:307
  • 評分評分:
  • 下載下載:1
  • 收藏至我的研究室書目清單書目收藏:0
本文提出一套自動變換車道系統,應用深度學習與專家系統建構變換車道決策網路,當前車車速過慢時,可評估周遭車輛的動態與變換車道的風險,進行變換車道決策。首先根據感測器所獲得的周遭車輛距離資訊,利用相對動態估測器估測周遭車輛與本車的相對動態、時間車距與碰撞時間等,作為決策網路的輸入資訊。接著依據舒適性限制進行變換車道軌跡規劃,當決策網路判斷為安全時,則進行變換車道行為;變換車道過程中持續進行風險評估,當決策網路在跨越車道線前判斷有碰撞風險時,立即取消變換車道行為。本文使用SUMO 蒐集其內建駕駛者模型變換車道行為資料,採用卷積神經網路與長短期記憶網路作為決策網路架構進行深度學習,並配合信心水準與基於規則的專家系統來輔助決策。應用基於模型預測控制的適應性巡航控制與側向位移追隨控制器來進行縱向與側向動態控制。最後利用CarSim 與SUMO 進行模擬驗證,其結果顯示本文所提出之演算法可有效評估周遭車輛風險,進行自動變換車道;並在過程中持續進行風險評估,若有危險時可取消變換車道,確保變換車道的安全。
An automatic lane changing (ALC) system is propsoed in this thesis. Deep learning and expert systems are used to establish a lane-changing decision-making network. When the preceding vehicle speed is too slow, the kinematcs of surrounding vehicles and the risk of lane change are evaluated to make lane-changing decisions. According to the relative distances of surrounding vehicles measured from distance sensors, a relative kinematics estimator is employed to estimate the relative speeds and accelerations, time headway (TH) and time-to-collision (TTC) between the surrounding vehicles and the host vehicle, which are used as the input information of the decision-making network. The ride comfort requirement is used to design the lane change trajectory. When the decision-making network determines that it is safe for lane change, the ALC system starts to change lane. Collision risks are continued to be assessed during lane change. If a collision risk is detected before lane crossing, lane change will be aborted. The lane-changing behavior data of the built-in driver in SUMO is collected for deep learning. An decision-making network is designed using convolutional neural network (CNN) and long short-term memory (LSTM). Cconfidence level and rule-based expert system are used to assist the decision-making. Adaptive cruise control (ACC) and lateral displacement control (LDC) based on model predictive control are used for longitudinal and lateral dynamics control. Finally, CarSim and SUMO are employed to verify the proposed algorithm. Simulation results show that the proposed algorithm can effectively assess the risks of surrounding vehicles and change lanes automatically. It can continue to perform risk assessment duing lane change. If there exists any risks, the lane change will be aborted to ensure the safety of lane change.
摘要 i
Abstract ii
誌謝 iv
目錄 v
表目錄 vii
圖目錄 ix
第一章 緒論 1
1.1 研究背景與動機 1
1.2 文獻回顧 3
1.3 研究目的 6
1.4 論文架構 7
第二章 深度學習 8
2.1 資料蒐集 8
2.1.1 變換車道前資料集 8
2.1.2 變換車道中資料集 15
2.2 變換車道前神經網路 18
2.2.1 變換車道前資料分析 18
2.2.2 基於二維卷積神經網路 19
2.3 變換車道中神經網路 27
2.3.1 變換車道中資料分析 27
2.3.2 基於二維卷積神經網路 28
2.3.3 基於二維卷積神經網路與長短期記憶網路 32
第三章 變道決策 37
3.1 變換車道前風險評估 37
3.2 變換車道中風險評估 40
第四章 軌跡追隨控制 44
4.1 軌跡規劃 44
4.2 模型預測控制 49
4.3 自適應巡航控制 52
4.4 側向位移追隨控制器 56
第五章 模擬結果 61
5.1 周遭車輛等速行駛情境 62
5.2 目標車道前車減速情境 67
5.3 原車道後車加速變道情境 72
第六章 結論與未來展望 77
參考文獻 79
附錄A 82
附錄B 85
附錄C 87
附錄D 88
附錄E 90
附錄F 92
符號彙編 93

[1] World Health Organization, “Global status report on road safety”,2018.
[2] 108年國道事故檢討分析報告,交通部高速公路局,2020.
[3] Suzanne E. Lee, Erik C.B. Olsen, and Walter W. Wierwille, “A Comprehensive Examination of Naturalistic Lane-Changes”, National Highway Traffic Safety Administration, March 2004.
[4] The Royal Society for the Prevention of Accidents, “Road Safety Factsheet,” July. 2017.
[5] Society of Automotive Engineers International, “Automated Driving – Levels of Driving Automation are Defined in New SAE International Standard J3016”, 2014
[6] Wilko Schwarting, Javier Alonso-Mora, and Daniela Rus, “Planning and Decision- Making for Autonomous Vehicles”, Annual Review of Control, Robotics, and Autonomous Systems, May 2018.
[7] M. Brännström, E. Coelingh and J. Sjöberg, “Model-based threat assessment for avoiding arbitrary vehicle collisions,” EEE Trans on Intell Transportation Systems, vol.11, no. 3, pp. 658–669, Sept. 2010.
[8] R. Labayrade, C. Royere and D. Aubert, “A collision mitigation system using laser scanner and stereovision fusion and its assessment,” IEEE Proceedings. intelligent vehicles symposium, June 2005.
[9] H. Jula, E.B. Kosmatopoulos and P.A. Ioannou, “Collision Avoidance Analysis for Lane Changing and Merging” IEEE Transactions on Vehicular Technology, vol. 49, no. 6, pp. 2295-2308, Nov. 2000.
[10] A. Jha, S. Mukherjee and D. Mohan, “Analysis of Headway and Lane Change Metrics of Indian Drivers using Naturalistic Driver Study Techniques,” IRCOBI Asia Conference Proceedings, May 2016.
[11] R. van der Host and J. Hogema, “Time-to-Collision and Collision Avoidance Systems,” 6th IC TCT workshop Salzburg, Jan. 1994.
[12] H. Tehrani, Q. H. Do, M. Egawa, K. Muto, K. Yoneda and S. Mita, "General behavior and motion model for automated lane change," 2015 IEEE Intelligent Vehicles Symposium (IV), Seoul, 2015, pp. 1154- 1159.
[13] 賴立達,“自動變換車道系統之決策與控制” ,碩士論文,國立臺北科技大學車輛工程系,台北,台灣,2020
[14] Z. Chen and X. Huang, "End-to-end learning for lane keeping of self-driving cars," 2017 IEEE Intelligent Vehicles Symposium (IV), Los Angeles, CA, 2017, pp. 1856-1860.
[15] F. Codevilla, M. Miiller, A. López, V. Koltun and A. Dosovitskiy, "End-to-End Driving Via Conditional Imitation Learning," 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, QLD, 2018, pp. 4693-4700.
[16] Y. Liu, X. Wang, L. Li, S. Cheng and Z. Chen, "A Novel Lane Change Decision-Making Model of Autonomous Vehicle Based on Support Vector Machine," in IEEE Access, vol. 7, pp. 26543-26550, 2019.
[17] C. Vallon, Z. Ercan, A. Carvalho and F. Borrelli, "A machine learning approach for personalized autonomous lane change initiation and control," 2017 IEEE Intelligent Vehicles Symposium (IV), Los Angeles, CA, 2017, pp. 1590-1595.
[18] Jianwei Gong, Youzhi Xu, Chao Lu and Guangming Xiong, "Decision-making model of overtaking behavior for automated driving on freeways," 2016 IEEE International Conference on Vehicular Electronics and Safety (ICVES), Beijing, 2016, pp. 1-6.
[19] Y. Wang and I. W. Ho, "Joint Deep Neural Network Modelling and Statistical Analysis on Characterizing Driving Behaviors," 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, 2018, pp. 1-6.
[20] E. Balal, R. L. Cheu, T. Sarkodie-Gyan, "A binary decision model for discretionary lane changing move based on fuzzy inference system", Transp. Res. C Emerg. Technol., vol. 67, pp. 47-61, Jun. 2016.
[21] C. Hoel, K. Wolff and L. Laine, "Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning," 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, 2018, pp. 2148-2155.
[22] X. Yang, L. Chen, W. Huaji, C. Dongpu, and V. Efstathios, “An Ensemble Deep Learning Approach for Driver Lane Change Intention Inference”, Transportation Research Part C: Emerging Technologies, June 2020.
[23] Z. Jun, W. Zhong Cheng, L. Fang, X. Cheng jun, R. Ting Ting, C. Jie, and L. Liu,”A Deep Learning Framework for Driving Behavior Identification on In-Vehicle CAN-BUS Sensor Data”, March 2019.
[24] A. Yuksel and S. Atmaca, "Driver’s black box: A system for driver risk assessment using machine learning and fuzzy logic," Journal of Intelligent Transportation Systems, vol. 25, no. 5, pp. 482-500, 2021.
[25] X. Zhang, J. Sun, X. Qi, and J. Sun, "Simultaneous modeling of car-following and lanechanging behaviors using deep learning," Transportation research part C: emerging technologies, vol. 104, pp. 287-304, 2019.
[26] T. Lee, B. Kim, K. Yi and C. Jeong, "Development of lane change driver model for closedloop simulation of the active safety system," 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC), Washington, DC, 2011, pp. 56-61.
[27] S. Ammoun, F. Nashashibi and C. Laurgeau, "An analysis of the lane changing manoeuvre on roads : the contribution of inter-vehicle cooperation via communication," 2007 IEEE Intelligent Vehicles Symposium, Istanbul, 2007, pp. 1095-1100.
[28] 張志豪,“自動緊急轉向系統之避障軌跡設計與追隨控制,碩士論文,國立臺北科技 大學車輛工程系,台北,台灣,2017.
[29] 陳偉杰,“應用碰撞時間與模型預測控制於防撞變換車道系統之設計” ,碩士論文,國立臺北科技大學車輛工程系,台北,台灣,2019
[30] L. Xiao, F. Gao, “A comprehensive review of the development of adaptive cruise control systems,” Vehicle System Dynamics, 48:10, 1167-1192, 2010.
[31] J. Zhang and P. Ioannou, “Longitudinal control of heavy trucks in mixed traffic: Environmental and fuel economy considerations,” IEEE Trans. Intel. Transport. Syst., vol. 7, no. 1, pp. 92–104, Jan., 2006.
[32] Adamu Abdullahi, and Sirin Akkaya, “Adaptive Cruise Control: A Model Reference Adaptive Control Approach,” 2020 24th International Conference onSystem Theory, Control and Computing, 2020.
[33] D. Morag, “Operating policies for personal rapid transit” U.S. DOT Urban Mass Transit Administration, Report No. RDD-8-74-2, 1974.
[34] D. Mackinnon, “High capacity personal rapid transit system developments” IEEE Trans. Veh. Technol. 24., pp. 8–14, 2015.
[35] T. Ming, W. Deng, S. Zhang, and B. Zhu, “MPC-Based Trajectory Tracking Control for Intelligent Vehicles,” SAE Technical Paper, 2016.
[36] CHARLES C. MAcADAM, “Application of an Optimal Preview Control for Simulation of Closed-Loop Automobile Driving,” IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS, VOL. SMC- II, NO. 6, JUNE 1981.
[37] Bo-Chiuan Chen, Bi-Cheng Luan, and Kangwon Lee, “Design of Lane Keeping System Using Adaptive Model Predictive Control,” 2014 IEEE International Conference on Automation Science and Engineering, Taipei, Taiwan, 2014.
[38] SUMO traffic simulator: https://sumo.dlr.de/index.html
[39] Wiedemann, R., 1974. Simulation des strassenverkehrsflusses. In: Proceedings of the Schriftenreihe des instituts fir Verkehrswesen der Universitiit Karlsruhe, Germany.
[40] Jakob.Erdmann, “Lane-Changing Model in SUMO,” Modeling Mobility with Open Data (pp. 105-123), 2015.
[41] H. Tehrani, Q. H. Do, M. Egawa, K. Muto, K. Yoneda and S. Mita, "General behavior and motion model for automated lane change," 2015 IEEE Intelligent Vehicles Symposium (IV), Seoul, 2015, pp. 1154-1159.
[42] Efstathios D. Gennatas, Jerome H. Friedmanb, Lyle H. Ungar, Romain Pirracchio, Eric Eaton, Lara G. Reichmann, Yannet Interian, José Marcio Luna, Charles B. Simone, Andrew Auerbach, Elier Delgado, Mark J. van der Laan, Timothy D. Solberg, and Gilmer Valdes, “Expert-augmented machine learning,” National Academy of Sciences, 117(9), 4571-4577, 2020.
[43] W. Yang, K. Wang, and W. Zuo, "Neighborhood component feature selection for highdimensional data," J. Comput., vol. 7, no. 1, pp. 161-168, 2012.
[44] H. Zhao, S. Sun, and B. Jin, "Sequential fault diagnosis based on LSTM neural network," Ieee Access, vol. 6, pp. 12929-12939, 2018.
[45] Wu Xiaorui and Yang Hongxu, “A Lane Change Model with the Consideration of Car Following Behavior”, 13th COTA International Conference of Transportation Professionals, pp. 2354-2361, 2013.
[46] R. van der Host and J. Hogema, “Time-to-Collision and Collision Avoidance Systems,” 6th IC TCT workshop Salzburg, Jan. 1994.
[47] 施昌瑋,“應用多物體追蹤於前方防撞警示系統之設計”,碩士論文,國立臺北科技 大學車輛工程系,台北,台灣,2010.
[48] L. L. Hoberock, “A Survey of Longitudinal Acceleration Comfort Studies in Ground Transportation Vehicles”, July 1976
[49] International standard orginization, “Intelligent transport systems — Adaptive Cruise Control systems — Performance requirements and test procedures,” 2002.
[50] G. M. Fitch, S. E. Lee, S. Klauer, J. Hankey, J. Sudweeks, and T. Dingus, “Analysis of Lane-Change Crashes and Near-Crash” NHTSA, June 2009.
[51] International standard orginization, “Intelligent transport systems — Lane keeping assistance systems (LKAS) — Performance requirements and test procedures,” 2014.
[52] L. Dai, Y. Xia, M. Fu and M. S. “Mahmoud, Discrete-Time Model Predictive Control”, 2012.

電子全文 電子全文(網際網路公開日期:20270810)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊