A method and device for multi-mode traffic arterial signal coordination control based on multi-agent cooperation

Abstract

The invention discloses a multi-mode traffic arterial signal coordination control method and device based on multi-agent cooperation. The method includes: multi-mode traffic arterial simulation calibration and flow generation; signal control multi-agent design at each intersection of the arterial line; construction of cooperation A multi-agent reinforcement learning framework for formula-value decomposition; training outputs agents at each intersection of multi-modal traffic arteries. The method provided by the invention regards the multi-mode traffic signal control of each intersection as an intelligent body, comprehensively considers the cooperation of each intersection of the main traffic line, and optimizes the training of the traffic signal control intelligent body with the goal of the overall traffic flow and delay of the main line , to provide management and control basis for road traffic managers, to achieve the overall optimal goal of traffic arteries, and to improve the level of urban road traffic services.

Description

technical field [0001] The invention relates to the field of urban traffic signal control, in particular to a multi-mode traffic arterial signal coordination control method and device based on multi-agent cooperation. Background technique [0002] In recent years, due to the rapid growth of traffic demand, road congestion, increased air pollution, and reduced transportation efficiency have seriously affected the economic development of the city and the daily life of citizens. In order to alleviate traffic problems, traffic arterial signal coordinated control is the preferred method in urban traffic control. Reasonable arterial control methods can effectively improve vehicle speed, traffic efficiency, and reduce fuel consumption and exhaust emissions. [0003] The traditional traffic arterial signal coordination control is mainly based on the green wave model, setting the public cycle time of each intersection on the arterial line, taking the number of vehicle parking, the wi...

AI Technical Summary

Problems solved by technology

In general, the existing research is biased towards the maximization of the benefits of vehicles and public transport on the main line. The efficiency of branch roads and single-point intersections is sacrificed in the model, and there is a lack of comprehensive consideration of multi-modal traffic such as public transport, pedestrians, and non-motorized vehicles on the main line. Single-point intersections with few arterial lines cooperate based on multimodal traffic adaptive control for global optimality of multimodal arterial lines: a microscopic study

Images