基于人機協同的車道保持輔助系統研究進展

秦增科; 郭烈; 馬躍; 岳明

doi:10.13374/j.issn2095-9389.2020.10.13.001

基于人機協同的車道保持輔助系統研究進展

doi: 10.13374/j.issn2095-9389.2020.10.13.001

大連理工大學汽車工程學院，大連 116024

基金項目: 國家自然科學基金資助項目（51975089，51575079）；國家重點研發計劃資助項目（2018YFE0197700）；遼寧省教育廳科學研究經費資助項目（LJYT201915）

詳細信息

通訊作者:
E-mail：guo_lie@dlut.edu.cn

中圖分類號: U471.1
計量
- 文章訪問數: 2028
- HTML全文瀏覽量: 965
- PDF下載量: 91
- 被引次數: 0
出版歷程
- 收稿日期: 2020-10-13
- 刊出日期: 2021-03-26

Overview of lane-keeping assist system based on human–machine cooperative control

School of Automotive Engineering, Dalian University of Technology, Dalian 116024, China

More Information

Corresponding author: E-mail: guo_lie@dlut.edu.cn

摘要

摘要: 基于人機動態協同控制的車道保持輔助系統有助于兼顧汽車的安全性與駕駛員的舒適性，分析了該系統在車道偏離決策模型、駕駛權動態分配及性能評估等方面的研究現狀和發展趨勢。在車道偏離決策模型方面，應根據駕駛員的狀態制定不同的決策模型，既可以建立自適應調節的決策模型，又應允許駕駛員根據自己的喜好和外部駕駛環境手動調整決策模型中預設的參數；在駕駛權分配方面，應探索更加合理的駕駛權動態分配方式，設計智能的優化算法或控制模型；在性能評估指標方面，應加入與降低人機沖突及減少駕駛員控制量相關的評估指標，制定科學完善的主觀評估體系。未來研究應該深度融合駕駛員因素，實時發出警報與主動干預，并能夠對系統進行完善的測試與評估。
- 協同控制 /
- 車道保持輔助系統 /
- 車道偏離 /
- 駕駛權分配 /
- 性能評估
Abstract: As the final stage of intelligent vehicle, traffic accidents can be effectively reduced by automatic driving. However, neither the technology nor the regulations are mature for autonomous driving. The lane-keeping assist system is one of the important components of the advanced driver-assistance system. When driver fatigue or inattention is detected, the system can effectively prevent the vehicle departure from the lane. Information such as vehicle status, driver status, and external environment can be used by the lane-keeping assist system based on human–machine dynamic cooperative control, thereby smoothly changing the driving rights between the driver and the automatic controller. The system can keep the vehicle in the lane while complying with the driver's intention, thereby ensuring vehicle safety and driver comfort. The research status and future development suggestions on lane-departure decision models, dynamic allocation of driving rights, and performance evaluation were analyzed in this paper. Regarding lane-departure decision models, different decision models considering the driver's state should be developed. The decision model can be established as an adaptive adjustment model and also should allow the manual adjustment of the preset parameters according to the driver’s preferences and the external driving environment. Concerning the allocation of driving rights, a more reasonable dynamic allocation of driving rights should be explored, and intelligent optimization algorithms or control models should be designed. Regarding performance evaluation indicators, evaluation indicators related to the reduction of human–machine conflict and the amount of control effort should be added. A scientific and complete subjective evaluation system should be developed. Future studies on lane-keeping assist system based on human–machine cooperative control should deeply integrate driver factors, issue real-time warnings and active intervention, and perform complete testing and evaluation of the system.
- cooperative control /
- lane-keeping assist system /
- lane departure /
- distribution of driving rights /
- performance evaluation

HTML全文

圖 1 加權求和型動態協同控制系統框圖

Figure 1. Block diagram of the weighted sum dynamic cooperative control system

下載: 全尺寸圖片幻燈片

圖 2 考慮車輛信息的動態協同控制系統框圖

Figure 2. Block diagram of dynamic cooperative control system considering vehicle information

下載: 全尺寸圖片幻燈片

圖 3 考慮駕駛員特性信息的動態協同控制系統框圖

Figure 3. Block diagram of the dynamic cooperative control system considering driver characteristic information

下載: 全尺寸圖片幻燈片

表 1 車道偏離決策模型的對比

Table 1. Comparison of lane-departure decision models

Model	Advantages	Disadvantages
TLC	The model warns the driver before the vehicle deviates from the lane, which gives the driver enough reaction time^[26].	The model will produce missing alarms when the distance between the vehicle and the lane is small and the angle between the driving direction and the line is small. The model assumes that the driving state of the vehicle is fixed during the warning time, which is out of reality and can cause false alarms^[27].
CCP	The current position of the vehicle is used as the prerequisite for warning, and the false alarm rate is low.	The effect of the warning is very dependent on the selection of the distance threshold.
FOD	The model can dynamically adjust the threshold based on different driving habits.	The vehicle velocity and direction are fixed during the preview time assumed by the model. The assumption deviates from reality and can cause false alarms^[28].
KBIRS	The camera calibration can be omitted, and only the images are used to determine whether to warn, and the effect of the warning is not affected by the line width, vehicle type, and lens parameters^[29].	The current development of the model is not perfect and is mainly focused on the perception of the natural scenes^[29]. Because of the diverse driving environments, only using the images will cause identification errors.
VRBS	The current position of the vehicle is used as the prerequisite for warning, and the false alarm rate is low^[30].	The effect of the warning is dependent on the selection of the distance threshold. The system may be unable to continuously detect the road edge, thereby hindering its function and adoption^[30].

下載: 導出CSV

表 2 駕駛權動態分配方式特點比較

Table 2. Comparison of characteristics of driving rights dynamic-allocation methods

Dynamic allocation of driving rights	Advantages	Disadvantages
Weighted sum	Good path-tracking performance	Human–machine conflict is likely to occur when the driver’s planned path is inconsistent with the controller’s planned path.
Weighted sum with weight coefficient	Due to the existence of weight coefficients, driver characteristics can be flexibly considered.	Abrupt changes in weight coefficients or switch between controllers are not conducive to flexible interaction.
Weight distribution in optimization problems	Since the driver and the controller have the same control target, there is little human–machine conflict.	Due to the rolling optimization in the MPC algorithm, it is not easy to guarantee real-time performance.

下載: 導出CSV

表 3 車道保持輔助系統的性能評估

Table 3. Performance evaluation of lane-keeping assist system

Performance evaluation method	Evaluation index	Evaluation content
Objective evaluation	Lateral velocity/lateral acceleration/lateral distance from target path	Path-tracking capability
	Yaw rate/side slip angle	Vehicle-handling stability
	Inversion ratio of steering wheel/standard deviation steering wheel angle/integral of steering angle and driver torque square	Driver’s control workload
	Driver torque and assist torque value/the product of driver and assist torque/conflict duration	Conflict between driver and controller
Subjective evaluation	Questionnaire	Driving comfort

下載: 導出CSV

259luxu-164

參考文獻(66)

[1]	Inagaki T. Smart collaboration between humans and machines based on mutual understanding. Ann Rev Control, 2008, 32(2): 253 doi: 10.1016/j.arcontrol.2008.07.003
[2]	Nobe S A, Wang F Y. An overview of recent developments in automated lateral and longitudinal vehicle controls // 2001 IEEE International Conference on Systems, Man and Cybernetics. e-Systems and e-Man for Cybernetics in Cyberspace (Cat. No. 01CH37236). Tucson, 2001: 3447
[3]	Song L H, Guo H Y, Wang F, et al. Model predictive control oriented shared steering control for intelligent vehicles // 29th Chinese Control and Decision Conference. Chongqing, 2017: 7568
[4]	Narote S P, Bhujbal P N, Narote A S, et al. A review of recent advances in lane detection and departure warning system. Pattern Recognit, 2018, 73: 216 doi: 10.1016/j.patcog.2017.08.014
[5]	Li K Q. Review of status and future prospects of automotive intelligent safety electronics. Chin J Automot Eng, 2011, 1(1): 4 doi: 10.3969/j.issn.2095-1469.2011.01.001 李克強. 汽車智能安全電子技術發展現狀與展望. 汽車工程學報, 2011, 1(1):4 doi: 10.3969/j.issn.2095-1469.2011.01.001
[6]	Zhao X J, Chen H Y. A study on lateral control method for the path tracking of intelligent vehicles. Automot Eng, 2011, 33(5): 382 趙熙俊, 陳慧巖. 智能車輛路徑跟蹤橫向控制方法的研究. 汽車工程, 2011, 33(5):382
[7]	Flemisch F, Kelsch J, L?per C, et al. Cooperative control and active interfaces for vehicle assitsance and automation // FISITA World Automotive Congress. München, 2008
[8]	Hu Y F, Qu T, Liu J, et al. Human-machine cooperative control of intelligent vehicle: recent developments and future perspectives. Acta Autom Sin, 2019, 45(7): 1261 胡云峰, 曲婷, 劉俊, 等. 智能汽車人機協同控制的研究現狀與展望. 自動化學報, 2019, 45(7):1261
[9]	Guo L, Li L H. Vehicle Driving Safety Assistance Technology. Beijing: Peking University Press, 2014 郭烈, 李琳輝. 汽車安全輔助駕駛技術. 北京: 北京大學出版社, 2014
[10]	ISO 17361—2017. Intelligent Transportation Systems–Lane Departure Warning Systems–Performance Requirements and Test Procedures. London: British Standards Institution, 2017
[11]	Lin C F, Ulsoy A G. Time to lane crossing calculation and characterization of its associated uncertainty. Intell Transp Syst J, 1996, 3(2): 85
[12]	Chang T H, Hsu C S, Wang C, et al. Onboard measurement and warning module for irregular vehicle behavior. IEEE Trans Intell Transp Syst, 2008, 9(3): 501 doi: 10.1109/TITS.2008.928243
[13]	Falcone P, Ali M, Sj?berg J. Predictive threat assessment via reachability analysis and set invariance theory. IEEE Trans Intell Transp Syst, 2011, 12(4): 1352 doi: 10.1109/TITS.2011.2158210
[14]	Li X P, Seignez E, Loonis P, et al. Vision-based estimation of driving inattention fused via Dempster-Shafer theory // IEEE International Conference on Cyber Technology in Automation, Control, & Intelligent Systems. Bangkok, 2012: 393
[15]	Nalla P, Goud G C L A, Padmaja V. Accident avoiding system using lane detection. Int J Rev Electron Commun Eng, 2013, 1(1): 1
[16]	Batavia P H. Driver-Adaptive Lane Departure Warning Systems. Pittsburgh: Carnegie Mellon University, 1999
[17]	Jung C R, Kelber C R. A lane departure warning system using lateral offset with uncalibrated camera // Intelligent Transportation Systems. Vienna, 2005: 102
[18]	Liu X H. Development of A Vision-Based Object Detection and Recognition System for Intelligent Vehicle [Dissertation]. Wisconsin: University of Wisconsin-Madison, 2000
[19]	Wu D H, Ye X J, Gu W K. An uncertain knowledge based real time road scene understanding algorithm. J Image Graph, 2002, 7(1): 69 doi: 10.3969/j.issn.1006-8961.2002.01.012 吳東暉, 葉秀清, 顧偉康. 基于不確定性知識的實時道路場景理解. 中國圖象圖形學報, 2002, 7(1):69 doi: 10.3969/j.issn.1006-8961.2002.01.012
[20]	Gonzalez-Mendoza M, Jammes B, Hernandez-Gress N, et al. A comparison of road departure warning systems on real driving conditions // 7th International IEEE Conference on Intelligent Transportation Systems. Washington, 2004: 349
[21]	Zhou Y, Xu R, Hu X F, et al. A lane departure warning system based on virtual lane boundary. J Inf Sci Eng, 2008, 24(1): 293
[22]	Godthelp H, Milgram P, Blaauw G J. The development of a time-related measure to describe driving strategy. Human Factors, 1984, 26(3): 257 doi: 10.1177/001872088402600302
[23]	Enkelmann W. Video-based driver assistance - from basic functions to applications. Int J Comput Vision, 2001, 45(3): 201 doi: 10.1023/A:1013658100226
[24]	Xu L H, Luo Q, Zhang L Y, et al. Research on variable virtual lane boundary for lane departure warning systems. Adv Transp Studies, 2014, 32: 37
[25]	Zhang W W, Song X L, Zhang G X. Real-Time lane departure warning system based on principal component analysis of grayscale distribution and risk evaluation model. J Cent South Univ, 2014, 21(4): 1633 doi: 10.1007/s11771-014-2105-2
[26]	Glaser S, Mammar S, Sentouh C. Integrated driver-vehicle-infrastructure road departure warning unit. IEEE Trans Veh Technol, 2010, 59(6): 2757 doi: 10.1109/TVT.2010.2049670
[27]	Van Winsum W, Brookhuis K A, de Waard D. A comparison of different ways to approximate time-to-line crossing (TLC) during car driving. Accident Anal Prev, 2000, 32(1): 47 doi: 10.1016/S0001-4575(99)00048-2
[28]	Jia L S. Research of Key Technologies for Lane Departure Warning System Considering the Driver Characteristics [Dissertation]. Wuhan: Huazhong University of Science and Technology, 2011 賈立山. 體現駕駛員特性的車道偏離預警系統關鍵技術研究[學位論文]. 武漢: 華中科技大學, 2011
[29]	Luo Q, Yuan J, Hu S G, et al. Review on the research of lane departure pre-warning system. Tech Autom Appl, 2015, 34(8): 1 羅強, 袁杰, 胡三根, 等. 車道偏離預警系統研究綜述. 自動化技術與應用, 2015, 34(8):1
[30]	Pilutti T, Ulsoy A G. Fuzzy-logic-based virtual rumble strip for road departure warning systems. IEEE Trans Intell Transp Syst, 2003, 4(1): 1 doi: 10.1109/TITS.2003.811810
[31]	Wu Y W. Research on Key Technologies of Lane Departure Driving Assistance System Based on Human-Machine Cooperation [Dissertation]. Changsha: Hunan University, 2013 吳乙萬. 人機協同下的車道偏離輔助駕駛關鍵技術研究[學位論文]. 長沙: 湖南大學, 2013
[32]	Angkititrakul P, Terashima R, Wakita T. On the use of stochastic driver behavior model in lane departure warning. IEEE Trans Intell Transp Syst, 2011, 12(1): 174 doi: 10.1109/TITS.2010.2072502
[33]	Guo L, Ge P S, Xia W X, et al. Lane-keeping control systems based on human-machine cooperative driving. China J Highway Transport, 2019, 32(12): 46 郭烈, 葛平淑, 夏文旭, 等. 基于人機共駕的車道保持輔助控制系統研究. 中國公路學報, 2019, 32(12):46
[34]	Navarro J. Human–machine interaction theories and lane departure warnings. Theoret Issues Ergonom Sci, 2017, 18(6): 519 doi: 10.1080/1463922X.2016.1243274
[35]	Ding J Y. Driver-Adaptive Lane Keeping Assistance Control [Dissertation]. Beijing: Tsinghua University, 2015 丁潔云. 自適應駕駛員特性的車道保持輔助控制[學位論文]. 北京: 清華大學, 2015
[36]	Wang W S, Zhao D, Han W, et al. A learning-based approach for lane departure warning systems with a personalized driver model. IEEE Trans Veh Technol, 2018, 67(10): 9145 doi: 10.1109/TVT.2018.2854406
[37]	Albousefi A A, Ying H, Filev D, et al. A two-stage-training support vector machine approach to predicting unintentional vehicle lane departure. J Intell Transp Syst, 2017, 21(1): 41 doi: 10.1080/15472450.2016.1196141
[38]	Editorial Department of China Journal of Highway and Transport. Review on China’s automotive engineering research progress: 2017. China J Highway Transport, 2017, 30(6): 1 doi: 10.3969/j.issn.1001-7372.2017.06.001 《中國公路學報》編輯部. 中國汽車工程學術研究綜述?2017. 中國公路學報, 2017, 30(6):1 doi: 10.3969/j.issn.1001-7372.2017.06.001
[39]	Mulder M, Abbink D A, Boer E R. Sharing control with haptics: Seamless driver support from manual to automatic control. Human Factors, 2012, 54(5): 786 doi: 10.1177/0018720812443984
[40]	Saito Y, Mitsumoto T, Raksincharoensak P. Effectiveness of a risk predictive shared steering control based on potential risk prediction of collision with vulnerable road users. IFAC-PapersOnLine, 2016, 49(19): 84 doi: 10.1016/j.ifacol.2016.10.466
[41]	Inoue S, Ozawa T, Inoue H, et al. Cooperative lateral control between driver and ADAS by haptic shared control using steering torque assistance combined with direct yaw moment control // 19th IEEE International Conference on Intelligent Transportation Systems (ITSC). Rio de Janeiro, 2016: 316
[42]	Tian Y T, Zhao Y B, Shi Y R, et al. The indirect shared steering control under double loop structure of driver and automation. IEEE/CAA J Autom Sin, 2020, 7(5): 1403
[43]	Sentouh C, Debernard S, Popieul J C, et al. Toward a shared lateral control between driver and steering assist controller. IFAC Proc Vol, 2010, 43(13): 404 doi: 10.3182/20100831-4-FR-2021.00071
[44]	Soualmi B, Sentouh C, Popieul J C, et al. Fuzzy Takagi-Sugeno LQ controller for a shared control of vehicle // 14th International IEEE Conference on Intelligent Transportation Systems. Washington, 2011: 956
[45]	Anderson S J, Peters S C, Pilutti T E, et al. Experimental study of an optimal-control-based framework for trajectory planning, threat assessment, and semi-autonomous control of passenger vehicles in hazard avoidance scenarios // Field and Service Robotics. Berlin: Springer, 2010: 59
[46]	Falcone P, Borrelli F, Asgari J, et al. Predictive active steering control for autonomous vehicle systems. IEEE Trans Control Syst Technol, 2007, 15(3): 566 doi: 10.1109/TCST.2007.894653
[47]	Iwano K, Raksincharoensak P, Nagai M. A study on shared control between the driver and an active steering control system in emergency obstacle avoidance situations. IFAC Proc Vol, 2014, 47(3): 6338 doi: 10.3182/20140824-6-ZA-1003.01015
[48]	Wang W S, Xi J Q, Chen H Y. Modeling and recognizing driver behavior based on driving data: A survey. Math Problems Eng, 2014, 2014: 245641
[49]	Duan L, Chen F. The future of advanced driving assistance system development in China // Proceedings of 2011 IEEE International Conference on Vehicular Electronics and Safety. Beijing, 2011: 238
[50]	Benloucif M A, Nguyen A T, Sentouh C, et al. A new scheme for haptic shared lateral control in highway driving using trajectory planning. IFAC-PapersOnLine, 2017, 50(1): 13834 doi: 10.1016/j.ifacol.2017.08.2223
[51]	Nguyen A T, Sentouh C, Popieul J C. Online adaptation of the authority level for shared lateral control of driver steering assist system using dynamic output feedback controller // 41st Annual Conference of the IEEE Industrial Electronics Society. Yokohama, 2015: 003767
[52]	Sentouh C, Nguyen A T, Benloucif M A, et al. Driver-automation cooperation oriented approach for shared control of lane keeping assist systems. IEEE Trans Control Syst Technol, 2019, 27(5): 1962 doi: 10.1109/TCST.2018.2842211
[53]	Jiang J J, Astolfi A. Shared-control for the lateral motion of vehicles // 2018 European Control Conference. Limassol, Cyprus, 2018: 225
[54]	Gao Z G, Chen W W, Tan D K, et al. Human-machine cooperative lane departure assist control considering driver manipulate failure. J Mech Eng, 2019, 55(16): 91 doi: 10.3901/JME.2019.16.091 高振剛, 陳無畏, 談東奎, 等. 考慮駕駛員操縱失誤的車道偏離輔助人機協同控制. 機械工程學報, 2019, 55(16):91 doi: 10.3901/JME.2019.16.091
[55]	Ma B, Liu Y L, Na X X, et al. A shared steering controller design based on steer-by-wire system considering human-machine goal consistency. J Franklin Inst, 2019, 356(8): 4397 doi: 10.1016/j.jfranklin.2018.12.028
[56]	Li R J, Li S B, Gao H B, et al. Effects of human adaptation and trust on shared control for driver-automation cooperative driving// SAE Technical Paper 2017-01-1987, 2017, https://doi.org/10.4271/2017-01-1987
[57]	Balachandran A, Brown M, Erlien S M, et al. Creating predictive haptic feedback for obstacle avoidance using a model predictive control (MPC) framework // 2015 IEEE Intelligent Vehicles Symposium. Seoul, 2015: 31
[58]	Gray A, Ali M, Gao Y Q, et al. A unified approach to threat assessment and control for automotive active safety. IEEE Trans Intell Transp Syst, 2013, 14(3): 1490 doi: 10.1109/TITS.2013.2262097
[59]	Zafeiropoulos S, Tsiotras P. Design of a lane-tracking driver steering assist system and its interaction with a two-point visual driver model // 2014 American Control Conference. Portland, 2014: 3911
[60]	Meng Y, Gan X, Bai G X. Path following control of underground mining articulated vehicle based on the preview control method. Chin J Eng, 2019, 41(5): 662 孟宇, 甘鑫, 白國星. 基于預瞄距離的地下礦用鉸接車路徑跟蹤預測控制. 工程科學學報, 2019, 41(5):662
[61]	Beal C E, Gerdes J C. Model predictive control for vehicle stabilization at the limits of handling. IEEE Trans Control Syst Technol, 2013, 21(4): 1258 doi: 10.1109/TCST.2012.2200826
[62]	Erlien S M, Fujita S, Gerdes J C. Shared steering control using safe envelopes for obstacle avoidance and vehicle stability. IEEE Trans Intell Transp Syst, 2016, 17(2): 441 doi: 10.1109/TITS.2015.2453404
[63]	Wang L M, Liu X L, Li C X, et al. Overview of internet of vehicles for 5G. Chin J Network Inf Secur, 2016, 2(6): 00064-1 王良民, 劉曉龍, 李春曉, 等. 5G車聯網展望. 網絡與信息安全學報, 2016, 2(6): 00064-1
[64]	Marino R, Scalzi S, Netto M. Nested PID steering control for lane keeping in autonomous vehicles. Control Eng Pract, 2011, 19(12): 1459 doi: 10.1016/j.conengprac.2011.08.005
[65]	Benloucif M A, Sentouh C, Floris J, et al. Online adaptation of the level of haptic authority in a lane keeping system considering the driver's state. Transp Res Part F, 2019, 61: 107 doi: 10.1016/j.trf.2017.08.013
[66]	Sentouh C, Soualmi B, Popieul J C, et al. Cooperative steering assist control system // 2013 IEEE International Conference on Systems, Man, and Cybernetics. Manchester, 2013: 941