Adaptive parking lot variable entrance and exit control method and device and storage medium

Abstract

The invention relates to a self-adaptive parking lot variable entrance and exit control method. The method comprises the steps of receiving queuing information of parking lot entrance and exit upstream and downstream road sections and parking lot internal road sections; predicting the number of vehicles leaving and entering the parking lot in unit time in each time period of the parking lot; calculating the minimum number of the outlets and the inlets; building a parking lot entrance and exit setting model based on multi-agent deep reinforcement learning by taking parking lot entrance and exit upstream and downstream road section queuing information, parking lot internal road section queuing information and the number of vehicles leaving and entering the parking lot in unit time as input and taking the minimum number of exits and entrances as constraint conditions, and training the model by utilizing interaction data; and inputting the upstream and downstream road sections of the parking lot entrance and exit, real-time queuing information of roads in the parking lot and the number of vehicles leaving and entering the parking lot in actual unit time, and outputting each entrance and exit setting of the parking lot by using the parking lot entrance and exit setting model. Compared with the prior art, the method has the advantages that dynamic and static information is considered at the same time, and setting is completed in a self-adaptive mode.

Description

technical field [0001] The invention relates to the technical field of parking lot facility control, in particular to an adaptive parking lot variable access control method based on traffic state perception and intelligent management and control. Background technique [0002] With the development of the automobile industry, the increasing demand for motor vehicles not only puts pressure on road traffic, but also makes it difficult to manage and control the parking system. Large-scale parking lots in cities often have multiple entrances and exits, and how to set the entrances and exits reasonably has become a major problem. Among them, the number of parking lot entrances and exits determines whether the traffic demand can be met, and the distribution of parking lot entrances and exits determines whether vehicles can efficiently enter or leave the parking lot. Improper entry and exit settings not only result in a degraded user experience, but also cause extreme stress on dyna...

AI Technical Summary

Problems solved by technology

Improper entrance and exit settings will not only lead to a decline in user experience, but also cause extreme pressure on the dynamic traffic outside the parking lot

Although the existing method for setting the entrance and exit of the parking lot can be determined based on information such as traffic volume, parking lot scale, and the level of the road connecting the entrance and exit of the parking lot, the traffic system is dynamic and often has obvious tidal phenomena. If the setting of the entrance and exit of the parking lot only Based on limited and fixed traffic information, it is difficult to meet the needs of vehicles leaving and entering, resulting in low traffic efficiency and even traffic paralysis

At the same time, the entrance and exit of the parking lot are the connecting points of dynamic and static traffic. The previous fixed parking lot entrance and exit setting method lacks self-adaptive ability. After the traffic system is impacted, it is difficult to quickly return to the normal level. limit

Images