logo

SCIENCE CHINA Information Sciences, Volume 63 , Issue 9 : 190203(2020) https://doi.org/10.1007/s11432-019-2983-0

A probabilistic risk assessment framework considering lane-changing behavior interaction

More info
  • ReceivedDec 1, 2019
  • AcceptedJul 7, 2020
  • PublishedAug 17, 2020

Abstract

Understanding the dynamic characteristics of surrounding vehicles and estimating the potential risk of mixed traffic can help reliable autonomous driving. However, the existing risk assessment methods are challenging to detect dangerous situations in advance and tackle the uncertainty of mixed traffic. In this paper, we propose a probabilistic driving risk assessment framework based on intention identification and risk assessment of surrounding vehicles. Firstly, we set up an intention identification model (IIM) via long short-term memory (LSTM) networks to identify the intention possibility of the surrounding vehicles. Then a risk assessment model (RAM) based on the driving safety field is employed to output the potential risk. Specifically, driving safety field can reflect the coupling relationship of drivers, vehicles, and roads by analyzing their interaction. Finally, an integrated risk evaluation model combining both IIM and RAM is developed to form a dynamic potential risk map considering multi-vehicle interaction. For example, in a typical but challenging lane-changing scenario, an intelligent vehicle can assess its driving status by calculating a risk map in real time that represents the risk generated by the estimated intentions of surrounding vehicles. Furthermore, simulations and naturalistic driving experiments are conducted in the extracted lane-changing scenarios, and the results verify the effectiveness of the proposed model considering lane-changing behavior interaction.


Acknowledgment

This work was supported by the Major Project of National Natural Science Foundation of China (Grant No. 61790561), National Science Fund for Distinguished Young Scholars (Grant No. 51625503), Intel Collaborative Research Institute on Intelligent and Automated Connected Vehicles (ICRI-IACV), the Joint Laboratory for Internet of Vehicle, and Ministry of Education - China Mobile Communications Corporation. We would also like to express our great thanks to the Ph.D. candidates, Hui XIONG and Yang LI, who participated in the discussion and optimized the study.


References

[1] González D, Pérez J, Lattarulo R, et al. Continuous curvature planning with obstacle avoidance capabilities in urban scenarios. In: Proceedings of 17th International IEEE Conference on Intelligent Transportation Systems (ITSC14), 2014. 1430--1435. Google Scholar

[2] Gonzalez D, Perez J, Milanes V. A Review of Motion Planning Techniques for Automated Vehicles. IEEE Trans Intell Transp Syst, 2016, 17: 1135-1145 CrossRef Google Scholar

[3] Tas O S, Kuhnt F, Zollner J M, et al. Functional system architectures towards fully automated driving. In: Proceedings of 2016 IEEE Intelligent Vehicles Symposium (IV), Gotenburg, 2017. 304--309. Google Scholar

[4] Predictive risk mapping of an environmentally-driven infectious disease using spatial Bayesian networks: A case study of leptospirosis in Fiji. PLoS Negl Trop Dis, 2018, 12: e0006857 CrossRef Google Scholar

[5] Guo H, Shen C, Zhang H. Simultaneous Trajectory Planning and Tracking Using an MPC Method for Cyber-Physical Systems: A Case Study of Obstacle Avoidance for an Intelligent Vehicle. IEEE Trans Ind Inf, 2018, 14: 4273-4283 CrossRef Google Scholar

[6] Wu C, Peng L, Huang Z. A method of vehicle motion prediction and collision risk assessment with a simulated vehicular cyber physical system. Transpation Res Part C-Emerging Technologies, 2014, 47: 179-191 CrossRef Google Scholar

[7] Kim J, Kum D. Collision Risk Assessment Algorithm via Lane-Based Probabilistic Motion Prediction of Surrounding Vehicles. IEEE Trans Intell Transp Syst, 2018, 19: 2965-2976 CrossRef Google Scholar

[8] Katrakazas C, Quddus M, Chen W H. Real-time motion planning methods for autonomous on-road driving: State-of-the-art and future research directions. Transpation Res Part C-Emerging Technologies, 2015, 60: 416-442 CrossRef Google Scholar

[9] Lee K, Peng H. Evaluation of automotive forward collision warning and collision avoidance algorithms. Vehicle Syst Dyn, 2005, 43: 735-751 CrossRef Google Scholar

[10] van Winsum W. The human element in car following models. Transpation Res Part F-Traffic Psychology Behaviour, 1999, 2: 207-211 CrossRef Google Scholar

[11] Li Y, Zheng Y, Wang J. Crash probability estimation via quantifying driver hazard perception. Accident Anal Prevention, 2018, 116: 116-125 CrossRef Google Scholar

[12] Archibald J K, Hill J C, Jepsen N A. A Satisficing Approach to Aircraft Conflict Resolution. IEEE Trans Syst Man Cybern C, 2008, 38: 510-521 CrossRef Google Scholar

[13] Minderhoud M M, Bovy P H L. Extended time-to-collision measures for road traffic safety assessment. Accident Anal Prevention, 2001, 33: 89-97 CrossRef Google Scholar

[14] Allen C, Ewing M, Keshmiri S, et al. Multichannel sense-and-avoid radar for small UAVs. In: Proceedings of IEEE/AIAA 32nd Digital Avionics Systems Conference (DASC), 2013. Google Scholar

[15] Khatib O. Real-time obstacle avoidance for manipulators and mobile robots. In: Proceedings of IEEE International Conference on Robotics and Automation, 1985. 500--505. Google Scholar

[16] Reichardt D, Shick J. Collision avoidance in dynamic environments applied to autonomous vehicle guidance on the motorway. In: Proceedings of the Intelligent Vehicles'94 Symposium, Paris, 1994. 74--78. Google Scholar

[17] Huang Y, Ding H, Zhang Y. A Motion Planning and Tracking Framework for Autonomous Vehicles Based on Artificial Potential Field Elaborated Resistance Network Approach. IEEE Trans Ind Electron, 2020, 67: 1376-1386 CrossRef Google Scholar

[18] Hu X, Chen L, Tang B. Dynamic path planning for autonomous driving on various roads with avoidance of static and moving obstacles. Mech Syst Signal Processing, 2018, 100: 482-500 CrossRef ADS Google Scholar

[19] Wang J, Wu J, Zheng X. Driving safety field theory modeling and its application in pre-collision warning system. Transpation Res Part C-Emerging Technologies, 2016, 72: 306-324 CrossRef Google Scholar

[20] Aoude G S, Luders B D, Lee K H, et al. Threat assessment design for driver assistance system at intersections. In: Proceedings of the 13th International IEEE Conference on Intelligent Transportation Systems, 2010. 1855--1862. Google Scholar

[21] Goerlandt F, Reniers G. On the assessment of uncertainty in risk diagrams. Saf Sci, 2016, 84: 67-77 CrossRef Google Scholar

[22] Xie G, Zhang X, Gao H. Situational Assessments Based on Uncertainty-Risk Awareness in Complex Traffic Scenarios. Sustainability, 2017, 9: 1582 CrossRef Google Scholar

[23] Belkhouche F. Modeling and Calculating the Collision Risk for Air Vehicles. IEEE Trans Veh Technol, 2013, 62: 2031-2041 CrossRef Google Scholar

[24] Havlak F, Campbell M. Discrete and Continuous, Probabilistic Anticipation for Autonomous Robots in Urban Environments,. arXiv Google Scholar

[25] Deo N, Trivedi M M. Multi-modal trajectory prediction of surrounding vehicles with maneuver based LSTMs. In: Proceedings of IEEE Intelligent Vehicles Symposium (IV), 2018. 1179--1184. Google Scholar

[26] Khosroshahi A, Ohn-Bar E, Trivedi M M. Surround vehicles trajectory analysis with recurrent neural networks. In: Proceedings of IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, 2016. 2267--2272. Google Scholar

[27] Tijerina L, Garrott W R, Stoltzfus D, et al. Eye Glance Behavior of van and Passenger Car Drivers during Lane Change Decision Phase. J Transportation Research Record, 2005, 37--43. Google Scholar

[28] Traffic Analysis Tools: Next Generation Simulation - FHWA Operations. https://ops.fhwa.dot.gov/trafficanalysistools/ngsim.htm. Google Scholar

[29] Yoshitake H, Shino M. Risk assessment based on driving behavior for preventing collisions with pedestrians when making across-traffic turns at intersections. IATSS Res, 2018, 42: 240-247 CrossRef Google Scholar

[30] Zou Y, Qu X. On the impact of connected automated vehicles in freeway work zones: a cooperative cellular automata model based approach. J Intelligent Connected Vehicles, 2018, 1: 1-14 CrossRef Google Scholar

[31] Zheng X, Huang H, Wang J. Behavioral decision-making model of the intelligent vehicle based on driving risk assessment. Comput-Aided Civil Infrastructure Eng, 2019, 16: mice.12507 CrossRef Google Scholar

[32] Zheng X, Huang B, Ni D. A novel intelligent vehicle risk assessment method combined with multi-sensor fusion in dense traffic environment. J Intelligent Connected Vehicles, 2018, 1: 41-54 CrossRef Google Scholar

[33] Seddon N. Observation of the Inverse Doppler Effect. Science, 2003, 302: 1537-1540 CrossRef ADS Google Scholar

[34] Zhang W, Dai J, Pei Y. Drivers' Visual Search Patterns during Overtaking Maneuvers on Freeway. IJERPH, 2016, 13: 1159 CrossRef Google Scholar

[35] Chen T, Wen H, Hu H. On-orbit assembly of a team of flexible spacecraft using potential field based method. Acta Astronaut, 2017, 133: 221-232 CrossRef ADS Google Scholar

[36] Guo H, Liu J, Dai Q. A Distributed Adaptive Triple-Step Nonlinear Control for a Connected Automated Vehicle Platoon With Dynamic Uncertainty. IEEE Internet Things J, 2020, 7: 3861-3871 CrossRef Google Scholar

[37] Krajewski R, Bock J, Kloeker L, et al. The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems. 2018,. arXiv Google Scholar

  • Figure 1

    (Color online) The framework of the comprehensive risk evaluation model. The combined model is composed of an intention identification model (IIM) and a risk assessment model (RAM). The IIM outputs the intention possibilities to the RAM. The RAM describes the dynamic magnitude and influence range of driving risk. Finally, a predictive risk map is generated to quantify the potential risk.

  • Figure 2

    (Color online) The structure of IIM. The input network includes a series of LSTM networks, and the output network generates the intention probabilities.

  • Figure 3

    (Color online) Schematic diagram of the predicted vehicle and its surrounding environment. The predicted vehicle $v_e$ is surrounded by six other vehicles $(V_{h1}-V_{h6})$, and the potential intentions of these vehicles are described by the lines with different colors. Each vehicle has its potential influence range shown as an ellipse in the figure.

  • Figure 4

    (Color online) Procedure of lane change. Three processes are defined in this figure according to the surrounding vehicle information and the trajectory of the predicted vehicle, where $\theta_s$ and $\theta_e$ are the heading angle threshold of the lane change start and end points, respectively.

  • Figure 5

    (Color online) The confusion matrix of intention identification. When the actual intention is keeping straight, the identification result turns to be the worst compared with recognizing the intention of turning left or turning right for two potential lanes, which will disturb the recognition process.

  • Figure 6

    (Color online) Elliptic constraint effect of road marking on traffic risk. The two dotted lines have the function of constraining vehicle $j$ to follow the centerline of its own lane, and hence when vehicle $j$ keeps straight, the influence range will turn to be in its own lane without any intention to change lane.

  • Figure 7

    (Color online) Force distribution of driving safety field under traffic marking restriction.

  • Figure 8

    (Color online) The predictive driving risk map. Combining IIM and RAM, a predictive risk map with intention possibility can describe the influence range and trend. In this example, we output the predicted vehicle with a 20% lane-keeping probability ($p_3=0.2$) and an 80% lane-changing probability ($p_1=0.8,p_2=0$) predicted by the IIM. Therefore, the distribution and magnitude of the field force are also proportional to 20% and 80% in the straight-line direction and the lane change direction.

  • Figure 9

    (Color online) Two different examples of driving risk maps. If there is no behavior prediction, it is assumed that all vehicles in the traffic map are stable and do not change their states suddenly. As time goes by, the behaviors of surrounding vehicles will change suddenly, resulting in possible collision risks when there is no early warning. Introducing the intention identification will ensure the reliability of planning and control in the subsequence stage. (a) An example of ‘Perception-Assessment-Planning' architecture; (b) an example of ‘erception-Prediction-Assessment-Planning' architecture.

  • Figure 10

    (Color online) Trajectory prediction of a surrounding vehicle.

  • Figure 11

    (Color online) Traffic risk maps of naturalistic driving scenarios. The top picture of each subgraph is the real scenario extracted from the highD Dataset. The red block in the figure represents the moving vehicle, the yellow label indicates the speed and ID of each vehicle, and the color depth in the map represents the risk intensity affected by the vehicle's speed, quality, and relative position with surrounding vehicles. (a) Naturalistic lane-keeping scenario; protectłinebreak (b) naturalistic cut-in scenario.

  • Table 1  

    Table 1Performance evaluation of different methods

    Intention Precision Recall Accuracy
    IIM SVM IIM SVM IIM SVM
    Turning left 0.925 0.903 0.884 0.833 0.874 0.832
    Keeping straight 0.785 0.716 0.859 0.828
    Turning right 0.927 0.907 0.880 0.835
  •   

    Algorithm 1 Risk assessment based on IIM and RAM

    Initialize $m_j,~r_{\rm~max},~v_j,~\theta_{ji},~k_{x,d},~k_{y,d},~A_1A_2,~B_1B_2,~r_0$;

    Get the initial state of the predicted vehicle $V_e^{(t)}$ and surrounding vehicles $V_{hi}^{(t)~}$;

    Set up the IIM;

    for $i=1$ to $n$ (traffic participants)

    Input the interaction state: $I^{(t)}=[V_h^{(t)~},S^{(t)~}~]~~,t=(T-T_p,\ldots~,T-1,T)$;

    Calculate the intention probability by using the Softmax function;

    Output the probability of the IIM: $p_m=P(l_m|I),\Omega=(p_1,p_2,p_3)$;

    end for

    for $m=1$ to $3$

    Define the driving risk force: $F_{ji,0}=E_{j,0}~(\frac{r_0}{k_{x,0}~x_{ji}^2+k_{y,0}~y_{ji}^2~}-\frac{1}{r_{\rm~max}~})$;

    Define the risk range: $r_{ji}=\frac{r'_{ji}}{\sqrt{k_{x,d} {\rm cos}^2\theta_{ji}+k_{y,d} {\rm sin}^2 \theta_{ji}}}$;

    Calculate the predictive driving risk force in this direction $F_{ki,m}=p_m~F_{ji,0}$;

    Output the predictive risk map in this direction;

    end for

    Calculate the total predictive driving risk force: $F_{ki}=\sum_{m=1}^3F_{ki,m}$;

    Output the total predictive risk map;

    Define the threshold force $F_{\rm~th}$ of active assistance based on the existed algorithm [19];

    if $F_{ki}>F_{\rm~th}$ then

    Output(“Danger from the surrounding vehicle" warning to vehicle $j$);

    else

    Output(“Safe driving" feedback to vehicle $j$);

    end if

Copyright 2020  CHINA SCIENCE PUBLISHING & MEDIA LTD.  中国科技出版传媒股份有限公司  版权所有

京ICP备14028887号-23       京公网安备11010102003388号