Traffic light control system based on cloud computing and fog computing collaborative reinforcement learning

Abstract

Provides a traffic light control system based on cloud computing and fog computing collaborative reinforcement learning. The provided traffic light control system includes a plurality of traffic light control devices and a cloud computing platform, and the plurality of traffic light control devices are coupled to the cloud computing platform; the traffic light control devices include: millimeter wave radar, laser radar, fusion A perception unit and an AIoT device; the millimeter-wave radar and the lidar are respectively coupled to the fusion perception unit, and the images or signals captured by the millimeter-wave radar and the laser radar are provided to the fusion perception unit; the fusion perception unit is the same as the fusion perception unit. The AIoT device of the traffic light control device to which it belongs is coupled, and the traffic situation information output by the fusion perception unit is provided to the AIoT device; the AIoT device provides part or all of the traffic situation information output by the fusion perception unit of the traffic light control device to which it belongs to the AIoT device. The cloud computing platform obtains control information from the cloud computing platform; the AIoT device controls the same traffic light control according to the traffic condition information provided by the fusion perception unit of the traffic light control device to which it belongs and the control information provided by the cloud computing platform The traffic light corresponding to the device.

Description

technical field [0001] The present application relates to information processing equipment and information processing systems, and in particular, to a traffic light control system using cloud computing and fog computing collaborative reinforcement learning. Background technique [0002] Urban traffic congestion has had a serious impact on the global economy and environment. Improving the efficiency of urban traffic signal control is one of the relatively "efficient and low-cost" methods to alleviate urban traffic congestion. Because the urban traffic environment is complex and uncertain, and its internal operation mechanism cannot be accurately analyzed and modeled, urban traffic signal control is more suitable for artificial intelligence. However, most of the current traffic light control methods use the strategy that each color signal light has a fixed duration, which often leads to the situation of "the red light cannot be used in the traffic jam section; the green light...

AI Technical Summary

Problems solved by technology

However, most of the current traffic light control methods use the strategy that each color signal light has a fixed duration, which often leads to the situation that "the red light on the congested road section cannot go; the green light on the smooth road section does not pass".

Images