Traffic Lights Dynamic Timing Algorithm Research Based On Vehicles Induction

With the development of urban modernization process of China,traffic problem have become a major problem that affects social development.Among,traffic congestion is the commonest problem,which has a great impact on traffic problem.Many scholars have devoted themselves to the study of traffic congestion and put forward the correlative solutions.Intelligent transportation system is an intelligent system which can effectively solve the traffic problem.In the important research of intelligent transportation system,the adaptive traffic lights control system is an effective way to alleviate urban traffic congestion.Due to the complexity and uncertainty of urban transportation system,the existing fix-time signal control system can not solve the traffic congestion problem efficiently.Therefore,this paper proposed the intelligent traffic control strategy by using the reinforcement learning algorithm based on the vehicle induction system,which can interact with environment continuously.Firstly,we design a traffic lights control strategy based on Q learning algorithm to reduce the average waiting time of vehicles at the intersection.Secondly,following the perspective of collaborative optimization,puts forward the traffic lights control strategy based on fuzzy Q learning algorithm,which uses fuzzy logic control to optimize the control action inline vehicles induction information from the collaborative intersection,to improve the convergence rate of Q learning algorithm.Finally,in order to improve the overall performance of the intelligent transportation system,puts forward the collaborative strategy of the vehicles induction based on Sarsa learning algorithm and traffic lights control based on Q learning algorithm,the collaborative of transportation system in data processing,strategy implementation and information generation etc,be better improve the performance of the transportation system.Based on the traffic lights control algorithm,by means of adaptive traffic lights control system,reinforcement learning,enhances the integration of fuzzy logic in traffic lights control algorithm which optimizes strategy of action selection,vehicles induction system,especially,the self-learning characteristic of reinforcement learning is applied to the dynamic transportation system.The experimental result shows that the traffic lights control strategy based on Q learning algorithm reduces the average waiting time ofvehicles and the congestion situation in the transportation system,and improves the performance of the transportation system.With this control strategy as the foundation,from the convergence speed of reinforcement learning algorithm and the overall performance of the transportation system to make better,the experimental result shows that the improved algorithm further improves the performance of the transportation system.