Multi-objective optimization control method and system for coordinated ramp merge of expressway networked vehicles

Abstract

The multi-objective optimization control method and system for expressway network-linked vehicle coordinated ramp merge firstly collects the state data of vehicles in the control area, and then determines the start time of control and the selection of the controlled vehicle according to the position of the ramp merge vehicle, through the data transmission module. The information is transmitted to the traffic control module, and the multi-objective control model based on artificial intelligence ramps merges with the vehicle trajectory in the control area of ​​the ramp to ensure efficient, safe and energy-saving operation of the overall road traffic while completing the ramps. Compared with the traditional method, the present invention greatly promotes the merging of vehicles on the ramp, and is different from other methods that convert the problem of merging the ramp into a problem of vehicle sequencing, greatly improves the efficiency of the merging of the ramp, and ensures that the main line The traffic efficiency and traffic safety of the ramp and the ramp reduce the energy consumption loss of the control vehicle and realize the maximization of the economic benefits of the high-speed system.

Description

technical field [0001] The invention belongs to the technical field of intelligent transportation vehicle-road coordination, and specifically relates to a multi-objective optimization control method and system for expressway network-connected vehicle coordinated ramp merge. Background technique [0002] With the rapid growth of the national economy and the continuous promotion of urbanization, the increase in regional trade has promoted the rapid growth of travel between cities, which has brought challenges to the efficient and safe operation of expressways. Among them, the on-ramp area, as a bottleneck affecting the traffic efficiency of expressways, is a particularly concerned issue in traffic management. A common approach to ramp control is to control the rate of on-ramp inflow by adjusting macroscopic traffic flow state variables such as density or flow. However, the purpose of ramp metering strategies is to prioritize efficiency on arterial lines and attempt to prevent...

AI Technical Summary

Problems solved by technology

That is, short-term action execution needs to take into account the impact on long-term goals, but for the sink problem, the rewards for on-ramp sink evaluation are sparse and long-term

In this case, it is difficult for traditional reinforcement learning methods to avoid local optima and instability when dealing with sparse reward problems, which affect the traffic efficiency and safety of vehicles in ramp areas.

[0004] In view of the above problems, the inventor has proposed a battery life-oriented on-ramp reinforcement learning method in related papers to initially solve the on-ramp import problem, but this method is mainly oriented to battery health issues and is an implementation case for specific application scenarios of new energy vehicles. However, it cannot be applied to the mixed ramp-in scene of traditional fuel vehicles and new energy vehicles; at the same time, the paper does not involve the selection of ramp-in vehicles to select the main road into the gap, and there is a lack of key links in the actual application of ramp-in

Images