城市道路网联混驾车辆分阶段动态轨迹控制方法

Phased Dynamic Trajectory Control Method for Mixed-Connected Vehicles in Urban Road Networks

随着城市的进步和不断发展,智能驾驶车辆逐渐代替路段中的部分人工驾驶车辆,但在未来较长时间内人工驾驶车辆并不会被完全取代,此时出现网联车与人工驾驶车辆的混驾环境,即目前以及未来时间内我们面临的驾驶环境。网联车与人工驾驶车辆驾驶行为在路段内相互干扰,造成混合车流行驶效率低下。为减弱2种车辆间的相互作用,提出一种分离混驾环境下网联车和人工驾驶车辆的分阶段动态车道引导算法(dynamic lane guidance algorithm for separating CAVs and HDVs in mixed traffic environment,SCHME)。通过该算法分离在交叉口上游路段的混合流车辆集合,调整智能驾驶车辆的行驶路线并进行实时动态更新,在满足运动学约束收敛的条件下,人工驾驶车辆根据网联车的动态路线进行相应调整,实现在每辆车广义安全损失成本最小的情况下提高路段内混驾环境下车辆运行效率。通过MATLAB模拟车辆在进入交叉口前的车辆运行状态,结果表明,SCHME算法可在广义安全损失成本最小的情况下提高路段内平均车辆通行效率(17.29%),同时当车辆优化数组越大,车辆集合距离交叉口越远时,智能驾驶车辆渗透率越低,每辆车的道路广义安全损失成本越低。

As urban development progresses,the connected and autonomous vehicles(CAVs)are gradually replacing some human-driven vehicles(HDVs)on road segments.However,HDVs will not be completely replaced in the foreseeable future.Therefore,the mixed traffic environment of CAVs and HDVs that has emerged at this time is the driving environment we are currently facing and will face in the future.The driving behavior of CAVs and HDVs interferes with each other on road sections,resulting in low efficiency of hybrid driving.In order to mitigate the interaction between CAVs and HDVs,a phased dynamic lane guidance algorithm for separating CAVs and HDVs in mixed traffic environments(SCHME)was proposed.The proposed algorithm separated the mixed flow vehicle set in the upstream section of the intersection,adjusted the driving routes of CAVs and performed real-time dynamic updates.Under the condition of meeting kinematic constraint and convergence,HDVs adjusted the routes according to the dynamic routes of CAVs,achieving an increase in vehicle operating efficiency in mixed driving environments within the road section under the condition of the minimum generalized safety loss cost for each vehicle.The operating state of vehicle before entering the intersection was simulated by MATLAB.It is concluded that the SCHME algorithm can improve the average vehicle traffic efficiency within a road section by 17%under the condition of the minimum generalized safety loss cost.At the same time,when the vehicle optimization array is larger and the vehicle set is farther away from the intersection,the lower the penetration rate of CAVs,the lower the generalized safety loss cost per vehicle.