考虑驾驶风格的车辆避障控制系统

Vehicle obstacle avoidance control system considering driving style

传统避障控制系统设计未考虑不同驾驶员的偏好,导致驾驶员对系统的接受度不高,为此提出融入驾驶风格量化的避障控制系统.采集多名熟练驾驶员的驾驶数据进行风格聚类,训练出基于支持向量机的分类器,实现对驾驶风格的在线识别.设计考虑驾驶风格的避障控制系统,将避障过程分为转向避障和恢复稳定2个阶段.在转向避障阶段,控制器通过跟踪相应驾驶风格对应的最大侧向加速度进行避障;在恢复稳定阶段,控制器控制车辆进行相邻车道中心线跟踪.综合考虑车辆的避障安全性和横摆稳定性,将直接横摆力矩控制子系统加入所提系统.构建系统仿真模型,分析不同驾驶风格下控制器避障操作和车辆状态响应的异同.开展驾驶员主观感受的问卷调查,结果表明,相较于传统避障控制系统,驾驶员对所提系统的接受度提升了16.58%.

An obstacle avoidance control system integrating the quantified driving style was proposed to resolve the problem that the traditional obstacle avoidance control system did not consider the preferences of different drivers,leading to low acceptance of the system by drivers.Firstly,the driving data from several skilled drivers were acquired for style clustering,and a classifier based on support vector machine was obtained to realize the online recognition of driving styles.Then,the obstacle avoidance control system considering driving style was designed,dividing the obstacle avoidance process into an obstacle avoidance by steering stage and a stability restoration stage.In the obstacle avoidance by steering stage,the controller avoided obstacles by tracking the maximum lateral acceleration of the corresponding driving style.In the stability restoration stage,the controller controlled the vehicle to track the center line of the adjacent lane.Moreover,in the whole obstacle avoidance process,a direct yaw-moment control subsystem was added considering the obstacle avoidance safety and yaw stability of the vehicle.Finally,a simulation model of the system was established to analyse the similarities and differences of the obstacle avoidance operation and the vehicle state response under different driving styles.A survey of drivers’subjective feelings was conducted,and the results showed that drivers’acceptance of the proposed system increased by 16.58%compared to the traditional obstacle avoidance system.