Adaptive Traffic Control Using Cooperative Communication Through Visible Light

Vieira, Manuel Augusto; Vieira, Manuela; Louro, Paula; Vieira, Pedro; Fernandes, Rafael

http://hdl.handle.net/10362/172764

Utilize este identificador para referenciar este registo.

Nome:	Descrição:	Tamanho:	Formato:
Adaptive_Trafc_Control_Using_Cooperative_Communication_Through.pdf		4.55 MB	Adobe PDF	Ver/Abrir

Contacte-nos

Autores

Vieira, Manuel Augusto

Resumo(s)

The study aims to create a Visible-Light Communication (VLC) system for secure vehicle management at intersections. This involves enabling communication between vehicles and infrastructure (V2V, V2I, and I2V) using headlights, streetlights, and traffic signals. Mobile optical receivers gather data, determine their location, and read transmitted information through joint transmission. An intersection manager coordinates traffic and communicates with vehicles through embedded Driver Agents. The system utilizes a "mesh/cellular" hybrid network configuration and encodes data into light signals emitted by transmitters. Optical sensors and filtering properties enable reception and decoding. The study demonstrates bidirectional communication, employing queue/request/response mechanisms and relative pose concepts for safe vehicle passage. A deep reinforcement learning model controls traffic light cycles, validated via simulation in a Simulation of Urban Mobility simulator. Results show that this adaptive traffic control system effectively collects detailed vehicle data and ensures secure communication within the short-range mesh network.

Descrição

Funding Information: Manuel Vieira, Manuela Vieira, Paula Louro, Pedro Vieira, and Rafael Fernandes declare that they do not have any conflicts of interest. This work was sponsored by FCT – Fundação para a Ciência e a Tecnologia, within the Research Unit CTS-Center of Technology and Systems, and by IPL/2022/POSEIDON_ISEL. This article does not contain any studies with human participants or animals performed by any of the authors. Publisher Copyright: © 2024, The Author(s).

Palavras-chave

Deep reinforcement learning model Light controlled intersection Queue distance Traffic control Vehicular communication “Mesh/cellular” hybrid network General Computer Science Computer Science Applications Computer Networks and Communications Computer Graphics and Computer-Aided Design Computational Theory and Mathematics Artificial Intelligence SDG 11 - Sustainable Cities and Communities