Urban traffic jam scheduling method based on reinforcement learning

Abstract

The invention discloses an urban traffic jam scheduling method based on reinforcement learning. The method comprises the following steps: acquiring real-time data of vehicle quantity information, vehicle queuing information and traffic light states of an urban road intersection through an image sensor and an inductive sensor; using a machine learning algorithm to form intersection road condition state data as scheduling model training data according to real-time data of vehicle number information, vehicle queuing information and traffic light states and in combination with intersection prior knowledge of road section limitation and lane information obtained from image information and reserve structured data; the scheduling model calculates a reward signal according to the passing effect of each lane of the intersection fed back by the environment and a reward function, so as to train the scheduling model; using a reinforcement learning algorithm to train a scheduling model based on the intersection road condition state data and the intersection traffic safety criterion; and taking intersection road condition state data as input, and outputting a traffic light state instruction and a corresponding traffic light control signal through the trained scheduling model.

Description

Technical field [0001] The present invention relates to the field of intelligent transportation, specifically to an urban traffic jam scheduling method based on reinforcement learning. Background [0002] With the continuous improvement of the people's economic level and the advancement of the urbanization process, the automobile as the most important means of transportation has entered thousands of households, and the problem of urban traffic congestion has become more and more serious. On the one hand, traffic jams will reduce social productivity, cause a lot of economic losses, and at the same time consume fuel resources and lead to serious carbon dioxide emission problems. Therefore, improving the efficiency of urban traffic and optimizing traffic dispatch methods occupy an important position in the field of modern transportation, of which traffic light intersection traffic is the most common bottleneck of traffic efficiency in urban road sections. [0003] The existing traff...

AI Technical Summary

Problems solved by technology

[0003] The existing traffic light control methods are mainly divided into two categories. One is the traditional rule-based signal light control algorithm, such as fixed duration, traffic flow, lane occupancy ratio and other algorithms. Such methods have a one-sided cognition of the scene. It is difficult to deal with vehicle flow scheduling in complex scenarios, and the efficiency of vehicle traffic is low

Images