The invention belongs to the field of artificial intelligence, and particularly relates to a multi-intersection travel time collaborative optimization method for an intelligent network connection vehicle. According to the method, an intelligent network connection vehicle is combined with a reinforcement learning method, a new reward function is provided, the average speed of vehicles in a traffic system is used as a reward value by the reward function, and the situation that the deceleration of vehicle driving in the traffic system is lower than a comfort level parameter is punished. And configuring an IDM car-following model for the vehicle by using SUMO software to simulate an artificial vehicle, improving calculation of comfort level parameters in the IDM car-following model, and calculating the comfort level parameters of the IDM car-following model according to the current traffic flow, the lane length and the expected speed of the vehicle. According to the invention, through combination of the reinforcement learning method and the ICV, the traffic flow rate and the traffic stability are effectively improved. Moreover, the ICV after reinforcement learning can effectively reduce the frequent change of the acceleration of the vehicle.
本发明属于人工智能领域,具体涉及一种智能网联车的多交叉口旅行时间协同优化方法;将智能网联车与强化学习方法结合,提出一个新的奖励函数,奖励函数将交通系统车辆的平均速度作为奖励值,对交通系统中出现车辆行驶的减速度低于舒适度参数的情况进行惩罚。并且利用SUMO软件将车辆配置IDM跟驰模型模拟人工车辆,对IDM跟驰模型中舒适度参数计算进行改进,根据当前的车流量,车道长度,车辆期望速度计算IDM跟驰模型的舒适度参数。本发明证明通过强化学习方法与ICV结合,有效的提高交通流率和提升交通稳定性。并且验证了经过强化学习后的ICV可以有效的减少车辆加速度频繁变换情况。
Multi-intersection travel time collaborative optimization method for intelligent network connection vehicle
一种智能网联车的多交叉口旅行时间协同优化方法
2022-10-11
Patent
Electronic Resource
Chinese
European Patent Office | 2025
|European Patent Office | 2024
|European Patent Office | 2024
|European Patent Office | 2024
|Intelligent network connection intersection emergency vehicle protection phase setting method
European Patent Office | 2024
|