With the development of connected and automated vehicles(CAVs),forming strategies could extend from the typically used first-come-first-served rules.It is necessary to consider passing priorities when crossing interse...With the development of connected and automated vehicles(CAVs),forming strategies could extend from the typically used first-come-first-served rules.It is necessary to consider passing priorities when crossing intersections to prevent conflicts.In this study,a hierarchical strategy based on a cooperative game was developed to improve safety and efficiency during right-turning merging.A right-turn merging conflict model was established to analyze the right-turning vehicle characteristics of the traffic flow.The proposed three-layered hierarchical strategy includes a decision-making layer,a task layer,and an operation layer.A decision-making-layer cooperative game strategy was used to determine the merging priority of straight-going traffic and right-turning flows.In addition,a task-layer cooperative game strategy was designed for the merging sequence.A modified consensus algorithm was utilized to optimize the speed of vehicles in the virtual platoon of the operation layer.Traffic simulations were performed on the PYTHON-SUMO integrated platform to verify the proposed strategy.The simulation results show that,compared with other methods,the proposed hierarchical strategy has the shortest travel time and loss time and performs better than other methods when the straight-going traffic flow increases during right-turning merging at the intersection.The proposed method shows superiority under a significant traffic flow with a threshold of 900 vehicle/(h·lane).This satisfactory application of right-turning merging might be extended to ramps,lane-changing,and other scenarios in the future.展开更多
基金the National Key Research and Development Program of China(No.2020YFB1600400)。
文摘With the development of connected and automated vehicles(CAVs),forming strategies could extend from the typically used first-come-first-served rules.It is necessary to consider passing priorities when crossing intersections to prevent conflicts.In this study,a hierarchical strategy based on a cooperative game was developed to improve safety and efficiency during right-turning merging.A right-turn merging conflict model was established to analyze the right-turning vehicle characteristics of the traffic flow.The proposed three-layered hierarchical strategy includes a decision-making layer,a task layer,and an operation layer.A decision-making-layer cooperative game strategy was used to determine the merging priority of straight-going traffic and right-turning flows.In addition,a task-layer cooperative game strategy was designed for the merging sequence.A modified consensus algorithm was utilized to optimize the speed of vehicles in the virtual platoon of the operation layer.Traffic simulations were performed on the PYTHON-SUMO integrated platform to verify the proposed strategy.The simulation results show that,compared with other methods,the proposed hierarchical strategy has the shortest travel time and loss time and performs better than other methods when the straight-going traffic flow increases during right-turning merging at the intersection.The proposed method shows superiority under a significant traffic flow with a threshold of 900 vehicle/(h·lane).This satisfactory application of right-turning merging might be extended to ramps,lane-changing,and other scenarios in the future.
文摘针对城市场景下巡飞弹自主协同饱和攻击问题,将其建模为分布式部分可观测马尔可夫决策过程(Dec-POMDPs),设计了确保巡飞弹在极小时间间隔内到达的专用奖励函数,并结合使用联合权重参数的奖励函数,采用循环多智能体深度确定性策略梯度算法(R-MADDPG)训练巡飞弹自主协同饱和攻击策略,使用蒙特卡罗方法分析指标成功率.仿真实验结果表明,在训练后的决策模型引导下,巡飞弹执行自主协同饱和攻击的任务成功率为93.2%,其中,机间避撞率为94.4%、空中突防成功率为99.5%,95.3%回合到达最大时间间隔小于0.4 s.
