Open AccessEnvironmental Adaptive Urban Traffic Signal Control Based on Reinforcement Learning Algorithm
Author(s) -
Yanming Feng,
Yongrong Wu
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1650/3/032097
Subject(s) - reinforcement learning , vissim , queue , computer science , algorithm , signal (programming language) , traffic simulation , stability (learning theory) , real time computing , artificial intelligence , engineering , machine learning , intersection (aeronautics) , transport engineering , computer network , programming language
Urban traffic signal control is an important part of the construction of intelligent regional traffic. Aiming at the problem of the optimal control strategy in urban traffic signals, this paper proposes environmental adaptive urban traffic signal control based on reinforcement learning algorithms. Through the continuous perception of the traffic environment, the position and speed of the vehicles in different environments are expressed in a matrix, and the parameters are continuously iteratively optimized through the reinforcement learning method to optimize the objective function (the vehicle that can pass the most in a limited time) to achieve the purpose of effective vehicle control. According to the traffic simulation software Vissim, it can be known that the algorithm proposed in this paper performs better in terms of average waiting queue length and global average speed compared with other algorithms, and the deep learning algorithm is significantly better than other algorithms in terms of stability. The average speed of the deep learning algorithm is increased by 9% compared with the baseline, and the average waiting queue length is reduced by 13.4% compared with the baseline. The experiments studied this time are sufficient to prove that the algorithm in this paper can adapt to the dynamically changing and complex urban traffic environment and has great research value.