基于行程时间的驾驶风格贝叶斯决策树动态识别

Dynamic recognition method of driving style from travel time based on Bayesian decision tree

驾驶风格是驾驶员对实际交通状况的态度和决策偏好,反映了驾驶员在车辆操作和运行期间的行为表现,驾驶员行为风格直接影响汽车安全预警系统的报警准确率。本文从汽车安全预警系统的研究角度出发,以驾驶风格为研究对象,利用GPS实时捕获的行程时间作为特征参数,建立基于贝叶斯决策树的汽车驾驶风格动态辨识模型;通过心理测试、实车实验以及模拟驾驶实验分别获取相应的数据,对模型进行验证。结果表明,该模型具有较高的可行性。

The driving style is the driver′s attitude towards the actual traffic situation and decision preferences,reflecting the driver′s behavior during the operation of the vehicle.The driver behavior style directly affects the alarm accuracy rate of the automobile safety early warning system.Based on the research perspective of automobile safety early warning system,this paper takes driving style as the research object,and uses GPS real-time captured travel time as the characteristic parameter to establish a dynamic identification model of driver′s driving style based on Bayesian decision tree.Psychological tests,real vehicle experiments and virtual driving experiments were designed,and the corresponding experimental data were collected to verify the model.The results show that the recognition method is feasible.