The invention discloses a pavement traffic signal lamp coordination control method based on reinforcement learning. Monitoring equipment which is arranged correspondingly to each crossing is included. Each monitoring equipment is connected to a remote server through a network module. The control method comprises the following steps that (1) the remote server calculates waiting time S through receiving a video signal; (2) the remote server analyzes and acquires a road congestion condition under each phase state ai; (3) the remote server acquires a feasible degree ciai under the phase state ai; when a traffic stream can pass through, the road is clear and the feasible degree ciai is 1; otherwise, congestion is generated in the road and the feasible degree ciai is 0; (4) the waiting time S and the feasible degree ciai are used to calculate an optimal driving phase state ai of the crossing; (5) the signal lamp is adjusted. The method in the invention is based on video information acquired in real time. Through coordinating and controlling traffic signal lamps of the plurality of crossings in one area, traffic passing efficiency is increased; a traffic flow of the area is maximized and a pavement traffic congestion condition is alleviated.
Pavement traffic signal lamp coordination control method based on reinforcement learning
2015-11-11
Patent
Electronic Resource
English
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Traffic signal lamp control method based on migration reinforcement learning
European Patent Office | 2023
|Crossroad traffic signal lamp control method based on reinforcement learning
European Patent Office | 2020
|Traffic signal lamp control method and system based on reinforcement learning
European Patent Office | 2021
|Traffic signal lamp control system and method based on reinforcement learning and dynamic timing
European Patent Office | 2021
|Deep Reinforcement Learning-based Traffic Signal Control
IEEE | 2023
|