为真实反映车辆在行驶过程中的风险,并准确预测未来潜在的驾驶风险,提出一种考虑目标车辆预测轨迹的预见性驾驶风险场模型.首先,根据场景中的地图信息和所有车辆的历史轨迹信息,来预测目标车辆的未来轨迹;然后,根据预测的目标车辆未来轨迹,以及规划的自车未来轨迹,计算自车与目标车辆之间的相对位置,以及它们之间靠近或远离的趋势;最后,通过构建的驾驶风险场模型计算自车在当前和未来时刻的驾驶风险.试验表明相比于传统的碰撞时间(Time to collision,TTC)方法,建立的预见性驾驶风险场模型能更真实地反映驾驶风险;相比于不考虑目标车辆轨迹预测的驾驶风险建模方法,建立的预见性驾驶风险场模型能判断自车与目标车辆之间靠近或远离的趋势,预测风险与真实风险的偏差约为5％,能够准确预测未来时刻的潜在驾驶风险.
Predictive Driving Risk Field Model
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.
NETL
NSTL
万方数据
