车联网环境下车辆博弈换道协作策略

A game-based lane-changing cooperation strategy supported by connected vehicle

交互协作驾驶为提高车辆换道安全和效率提供了一条有效途径,然而可靠的人机协作(HMC)机制是其能有效运行的关键。基于博弈均衡思想,提出一种车联网环境下的车辆博弈换道协作策略。在捕捉和分析驾驶员不同换道类型的行为特征及驾驶期望的基础上,建立车辆换道协作博弈模型,通过求解模型的纳什均衡获取最优换道协作决策方案。特别地,设计了一种换道收益变量标准化的评估方法,并在强制换道中引入了与换道压力相关的协作激励用于构建收益函数。然后,基于实测交通数据对模型进行校准和检验,检验结果显示,模型的平均绝对误差在10%以内,具有良好的准确性和可靠性。最后,对有/无换道协作策略两种情况下的路段交通进行了仿真实验,结果表明,博弈换道协作策略可以有效地提高车辆的换道和通行效率,提升路段通行能力。

Interactive cooperative driving is a promising approach to improve the safety and efficiency of vehicle lane-changing.Reliable human-machine cooperation(HMC)mechanism is the key to its effective operation.Based on the idea of game equilibrium,a game-based cooperation strategy for vehicle lane-changing under connected environment is proposed.On the basis of capturing and analyzing the behavior characteristics and driving expectations of drivers with different lane changing types,the vehicle lane-changing cooperative game model is established,and the optimal cooperative scheme is obtained by solving the Nash equilibrium of the model.In particular,an evaluation method for standardization of lane-changing payoff variables is designed,and a cooperative incentive related to lane change pressure is introduced to construct the payoff function in the mandatory lane-changing.Then,the model is calibrated and tested based on the actual traffic data.The test result shows that the average absolute error of the model is less than 10%,which has good accuracy and reliability.Finally,traffic simulations are carried out on the road section in the presence/absence of the lane-changing cooperation strategy.The result indicates that the proposed game lane-changing cooperation strategy can effectively improve the efficiency of lane-changing for vehicles,and increase the traffic capacity of the road section.