Predictive Driving Risk Field Model

doi:10.3901/JME.2024.10.160

Abstract

Abstract: In order to accurately assess driving risks and predict potential hazards, it is necessary to consider the trajectory predictions of target vehicles. To address this issue, a predictive driving risk field model that takes into account the future trajectories of target vehicles is proposed. The model is comprised of three main steps. First, this study predict the future trajectories of target vehicles based on the map information in the scene and the historical trajectory information of all vehicles. Second, this study calculate the relative positions and motion trends (i.e., approaching or moving away from each other) between the ego vehicle and its target vehicles, based on the predicted future trajectories of target vehicles and the planned future trajectory of the ego vehicle. Finally, this study use the constructed driving risk field model to calculate the driving risk of the ego vehicle at both the current and future time intervals. The experimental results demonstrate that our predictive driving risk field model is more effective at reflecting driving risks compared to the traditional time-to-collision(TTC) method. Moreover, the deviation between predicted risk and real risk is about 5%. It shows that our model provides more accurate predictions of potential driving risks in the future, compared to a driving risk modeling method that does not consider the trajectory predictions of target vehicles.

Key words: driving risk field, trajectory prediction, predictive driving, risk assessment, intelligent vehicle

CLC Number:

U461

CHU Duanfeng, PENG Saiqian, HU Haiyang, PI Dawei. Predictive Driving Risk Field Model[J]. Journal of Mechanical Engineering, 2024, 60(10): 160-170.

References

[1] MATSUMI R，RAKSINCHAROENSAK P，NAGAI M. Autonomous braking control system for pedestrian collision avoidance by using potential field[J]. IFAC Proceedings，2013，46(21):328-334.
[2] THOMAS S，THORSTEN B. From robotics to automotive:Lane-keeping and collision avoidance based on elastic bands[J]. Vehicle System Dynamics，2008，46(7):597-619.
[3] 王建强，吴剑，李洋. 基于人-车-路协同的行车风险场概念、原理及建模[J]. 中国公路学报，2016，29(1):105-114. WANG Jianqiang，WU Jian，LI Yang. Concept，principle and modeling of driving risk field based on driver-vehicle-road interaction[J]. China Journal of Highway and Transport，2016，29(1):105-114.
[4] WANG Jianqiang，WU Jian，ZHENG Xunjia，et al. Driving safety field theory modeling and its application in pre-collision warning system[J]. Transportation Research Part C:Emerging Technologies，2016，72，306-324.
[5] LI Mingjun，SONG Xiaolin，CAO Haotian，et al. Shared control with a novel dynamic authority allocation strategy based on game theory and driving safety field[J]. Mechanical Systems and Signal Processing，2019，124:199-216.
[6] 李林恒，甘婧，曲栩，等. 智能网联环境下基于安全势场理论的车辆跟驰模型[J]. 中国公路学报，2019，32(12):76-87. LI Linheng，GAN Jing，QU Xu，et al. Car-following model based on safety potential field theory under connected and automated vehicle environment[J]. China Journal of Highway and Transport，2019，32(12)，76-87.
[7] 李林恒，甘婧，曲栩，等. 智能网联环境下基于安全势场理论的车辆换道模型[J]. 中国公路学报，2021，34(6):184-195. LI Linheng，GAN Jing，QU Xu，et al. Lane-changing model based on safety potential field theory under the connected and automated vehicles environment[J]. China Journal of Highway and Transport，2021，34(6):184-195.
[8] RASEKHIPOUR Y，KHAJEPOUR A，CHEN S K，et al. A potential field-based model predictive path-planning controller for autonomous road vehicles[J]. IEEE Transactions on Intelligent Transportation Systems，2017，18(5):1255-1267.
[9] 田野，裴华鑫，晏松，等. 车路协同环境下行车风险场模型的扩展与应用[J]. 清华大学学报，2022，62(3):447-457. TIAN Ye，PEI Huaxin，YAN Song，et al. Extended driving risk field model for i-VICS and its application[J]. Journal of Tsinghua University，2022，62(3):447-457.
[10] CASAS S，LUO W，URTASUN R. IntentNet:Learning to predict intention from raw sensor data[C]//Proceedings of the 2nd Conference on Robot Learning. Zurich，Switzerland:PMLR，2018，87:947-956.
[11] CHAI Y，SAPP B，BANSAL M，et al. MultiPath:Multiple probabilistic anchor trajectory hypotheses for behavior prediction[C]//Proceedings of the 3nd Conference on Robot Learning. Osaka，Japan:PMLR，2020，100:86-99.
[12] GAO Jiyang，SUN Chen，ZHAO Hang，et al. VectorNet:Encoding HD maps and agent dynamics from vectorized representation[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle，USA，2020:11522-11530.
[13] LIANG Ming，YANG Bin，HU Rui，et al. Learning lane graph representations for motion forecasting[C]//16th European Conference on Computer Vision (ECCV 2020). Glasgow，UK，2020:541-556.
[14] GU Junru，SUN Chen，ZHAO Hang. DenseTNT:End-to-end trajectory prediction from dense goal sets[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal，Canada，2021:15283-15292.
[15] VASWANI A，SHAZEER N，PARMAR N，et al. Attention is all you need[C]//31st Annual Conference on Neural Information Processing Systems (NIPS). Long Beach，CA:2017:6000-6010.
[16] 吴剑. 考虑人-车-路因素的行车风险评价方法研究[D]. 北京:清华大学，2015. WU Jian. Research on driver-vehicle-road factors considered driving risk evaluation method[D]. Beijing:Tsinghua University，2015.
[17] CHANG M F，LAMBERT J，SANGKLOY P，et al. Argoverse:3D tracking and forecasting with rich maps[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach，CA:2019，8740-8749.
[18] 李文博，刘羽婧，张峻铖，等. 驾驶员情绪-驾驶风险机理分析[J]. 机械工程学报，2022，58(22):379-394. LI Wenbo，LIU Yujing，ZHANG Juncheng，et al. Analysis of the influence mechanism of driver's emotion on driving risk[J]. Journal of Mechanical Engineering，2022，58(22):379-394.