基于动态风险评估的车辆辅助驾驶行为决策

Vehicle Assisted Driving Behavior Decision-Making Based on Dynamic Risk Assessment

为保障高级别辅助驾驶系统决策的安全性和可靠性,提出一种基于动态场景行车风险评估的车辆辅助驾驶行为决策方法。首先,基于势场理论分别建立障碍物风险评估模型和虚拟车道风险评估模型,用以描述动态交通场景对行驶车辆所产生的驾驶风险;其次,根据车辆换道过程将换道行为分为换道动机产生和目标车道安全决策两个阶段,提出换道场景风险评估指标,制定安全换道规则,采用公开数据集分析验证了换道场景下风险评估指标的表征能力;之后,基于实时交通环境信息,确定车道内驾驶行为决策方法,实现多种驾驶场景下的行为安全决策;最后,在PreScan/CarSim/Simulink联合仿真平台和实车试验平台上对所提出的车辆辅助驾驶行为决策方法进行验证。结果表明,所提出的风险评估模型和驾驶行为决策方法,能够准确识别并评估行车风险,并实时决策车辆应采取的合理驾驶行为,有效保证了高级别辅助驾驶系统的行车安全。

In order to ensure the safety and reliability of the high-level assisted driving system decision-making,a vehicle assisted driving behavior decision-making method based on dynamic driving risk assessment is proposed.Firstly,an obstacle risk assessment model and a virtual lane risk assessment model are established based on the potential field theory,which are used to describe the driving risk caused by dynamic traffic scenarios to the driving vehicle.Secondly,lane change behavior is divided into two stages according to the vehicle lane change pro-cess,which are lane change motivation generation and target lane safety decision-making.Further,the risk assess-ment indicator for lane change scenarios is proposed to formulate safe lane change rules,and the public data set is used to analyze and verify the risk assessment representation capability in lane change scenarios.Then,based on re-al-time traffic environment information,the driving behavior decision-making method in lane is determined to achieve safe decision-making in various driving scenarios.Finally,the proposed vehicle assisted driving behavior decision-making method is verified on the PreScan/CarSim/Simulink joint simulation platform and real vehicle road test platform.The results show that the proposed risk assessment model and driving behavior decision-making meth-od can accurately identify and evaluate driving risk,and decide the vehicle driving behavior in real time and ratio-nally,which effectively ensures the driving safety of the high-level assisted driving system.