Inicio  /  Applied Sciences  /  Vol: 13 Par: 11 (2023)  /  Artículo
ARTÍCULO
TITULO

A Bus Signal Priority Control Method Based on Deep Reinforcement Learning

Wenchao Shen    
Liang Zou    
Ruisheng Deng    
Hongyu Wu and Jiabin Wu    

Resumen

To investigate the issue of multi-entry bus priority at intersections, an intelligent priority control method based on deep reinforcement learning was constructed in the bus network environment. Firstly, a dimension reduction method for the state vector based on the key lane was proposed, which contains characteristic parameters such as the bus states, the flow states, and the signal timing. Secondly, a control action method that can adjust phase sequence and phase green time at the same time was proposed under the constraints of maximum green and minimum green. Furthermore, a reward function, which can be uniformly converted into the number of standard cars, was established focusing on the indexes such as the busload and maximum waiting time. Finally, through building an experimental environment based on SUMO simulation, a real-time bus signal priority control method based on deep reinforcement learning was constructed. The results show that the algorithm can effectively reduce the waiting time of buses without affecting overall traffic efficiency. The findings can provide a theoretical basis for the signal control method considering bus priority and improve the operation efficiency of public transport.

 Artículos similares

       
 
Zupeng Liu, Keping Li, Ying Ni     Pág. 1585 - 1596
Arterial coordinated control and transit signal priority are effective ways to alleviate traffic congestion. Transit vehicles must enter the bus stops for passenger boarding and alighting. The research of transit signal priority should consider the impac... ver más

 
Wataru Nishio, Hidekazu Suzuki, Yukimasa Matsumoto     Pág. 3909 - 3921
One of methods to improve the convenience and quality of service provided by bus service operators is to implement a bus location system capable of providing positional and operation related information to the users. We have previously proposed and imple... ver más

 
Nikolai Byshov, Arkadii Simdiankin, Ivan Uspensky     Pág. 107 - 111
A new solution for the problem of traffic safety regulation with use of RFID technologies is suggested. Traffic safety enhancement is achieved by polling with a modulated radio signal of all electronic analogues of traffic signs and traffic lights repres... ver más

 
Karl Bang, Johan Wahlstedt, Leif Linse     Pág. 75 - 86
A detailed procedure for capacity analysis of signalized intersections was first produced in 1976 and presented at the TRB Annual meeting (Bang, Hansson, Peterson 1978). In the eighties computer aids (named CAPCAL) based on this methodology were develope... ver más