Self-adaptive parking lot exit barrier gate control method and device and storage medium

Abstract

The invention relates to a self-adaptive parking lot exit barrier gate control method. The method comprises the following steps: receiving downstream and internal queuing information of a parking lot exit; predicting the number of vehicles driving away from each exit in unit time; calculating forbidding time of different exit barrier gate control modes; the method comprises the following steps: taking parking lot exit downstream and internal queuing information and an allowable maximum queuing length as input parameters, and constructing an adaptive parking lot exit barrier gate control model by using a multi-agent deep reinforcement learning framework, establishing a corresponding commentator network and a corresponding performer network, outputting expected benefits, and iteratively training the networks until a reward function converges by utilizing interaction data to obtain the maximum expected benefits; and inputting parking lot exit downstream and internal real-time queuing information and an allowable maximum queuing length, and outputting parking lot exit barrier gate control by using the model. Compared with the prior art, the method has the advantages of consideration of dynamic and static traffic, high flexibility and the like.

Description

technical field [0001] The invention relates to the technical field of parking lot exit gate control, in particular to an adaptive parking lot exit gate control method, device and storage medium based on traffic state perception. Background technique [0002] With the development of the automobile industry, the increasing demand for motor vehicle travel not only puts pressure on road traffic, but also makes it difficult to manage and control the parking system. The control flexibility of existing parking lot gates is limited, and it is difficult to adjust according to dynamic traffic conditions, and it is easy to release too many or too few vehicles within a certain period of time, resulting in traffic congestion on the ground or in the parking lot. At the same time, the parking lot of a large building often has multiple exits, and the flow distribution among the exits is not balanced, which often leads to serious congestion of individual exits. [0003] In the existing par...

AI Technical Summary

Problems solved by technology

For example, inductive barrier gate control usually only raises the bar when the queuing length of the road downstream of the parking lot exit is lower than the specified value and there are vehicles that need to leave the parking lot. Although the inductive barrier gate control can reduce the impact on the downstream road of the parking lot exit, However, compared with the fixed gate control, there will be a larger queue in the parking lot during peak hours

In fact, the state of dynamic traffic and static traffic changes all the time. It is difficult to use the accurate period length and queue length as the standard to control the barrier gate of the parking lot. Impact

Images