基于混合模糊多人多目标非合作博弈的车道选择模型

建立汽车安全驾驶辅助系统（包括安全驾驶预警系统）是保证交通安全的有效手段.准确预测车辆集群态势是汽车安全辅助驾驶的前提，车道选择是车辆集群态势发生转移最为根本的原因，也是交通流理论研究的基本内容.以往研究没有综合考虑车辆集群复杂态势下各运动实体特征及其操控者类型，以及多个车道间车辆的冲突对车道选择的影响.为此，本文综合考虑各运动实体特征及其操控者类型，基于混合模糊多人多目标非合作博弈方法，建立城市快速路基本路段上的驾驶员车道选择模型.通过分析各方驾驶员在不同车道选择策略下的收益，确定换道博弈的Nash均衡，得到驾驶员最优车道选择策略.研究结果表明:基于混合模糊多人多目标非合作博弈方法建构的驾驶员车道选择模型，其预测准确率可达到85.2%.

Drivers' Lane Choice Model Based on Mixed Fuzzy Multi-person and Multi-objective Non-cooperative Game

Vehicle safety driving assistance system (including driving safety alerting system) is an effective means to ensure traffic safety while accurate prediction of vehicle cluster situation is the premise of automobile safety assistant driving system. The drivers' lane choice process is not only the root cause of the transformation of vehicle cluster situation, but also the basic topic of traffic flow research. Previous studies do not synthetically consider the characteristics of individual traffic entities and the types of manipulators under the complex vehicle cluster situation, neither the influence of vehicles conflicts under multiple lanes on lane choice is taken into account. Therefore, in this paper, considering the types of vehicle manipulators and the characteristics of each movement entity, the model of drivers' lane choice on basic segment of urban expressway is built based on mixed fuzzy multi-person and multi-objective non-cooperative game. Drivers' profits under the different combinations of lane choice behaviors are analyzed, Nash equilibrium in the game process is confirmed, and the drivers' optimal lane choice strategy in a dynamic game is obtained. The results show that the model's prediction accuracy of lane change reaches 85.2%.