Heavy vehicle traffic is one of the main problems in large cities, and in Brazil, where the competent authorities have not trained road networks, overcrowding in traffic causes even more obstacles. The applications of computational intelligence techniques in traffic are very broad, with an emphasis on intelligent traffic lights. For the design of intelligent traffic lights, this work proposes the use of Fuzzy Logic, but its main objective is the automatic generation of Fuzzy systems. In order to achieve this objective, the SUMO traffic simulation software was used, which allowed the development of three intersection scenarios controlled by traffic lights. In these scenarios, the traffic performance was evaluated from different adjustments in the pertinence functions and in the set of rules of the Fuzzy system that controls the traffic lights, and these adjustments were made by the AG (Genetic Algorithm) and PSO (Particle Swarm Optimization) algorithms. When comparing traffic performance with traffic lights controlled by Fuzzy and optimized Fuzzy, there are quite significant improvements in the traffic variables analyzed, such as waiting time and the queue size of cars. Thus, this work shows the importance of using evolutionary Fuzzy models to optimize parameters. Resumo: O tráfego intenso de veículos é um dos principais transtornos nas grandes metrópoles, e no Brasil, onde as autoridades competentes não capacitaram as redes viárias, a superlotação no trânsito causa ainda mais entraves. As aplicações das técnicas de inteligência computacional no trânsito são muito amplas, com destaque para os semáforos inteligentes. Para o projeto de semáforos inteligentes, este trabalho propõe o emprego da Lógica Fuzzy, mas tem como objetivo principal a geração automática de sistemas Fuzzy. Para a realização desse objetivo, foi empregado o software de simulação de tráfego SUMO, que permitiu a elaboração de três cenários de cruzamentos controlados por semáforos. Nesses cenários foram avaliados o desempenho dos tráfegos a partir de diferentes ajustes nas funções de pertinência e no conjunto de regras do sistema Fuzzy que controla os semáforos, sendo que esses ajustes foram efetuados pelos algoritmos AG (Algoritmo Genético) e PSO (Particle Swarm Optimization). Quando comparado o desempenho do tráfego com semáforos controlados por Fuzzy e Fuzzy otimizado, tem-se melhorias importantes nas variáveis de trânsito analisadas, como tempo de espera e tamanho da fila de carros. Assim, este trabalho evidencia a importância de se empregar modelos Fuzzy evolucionários na otimização de parâmetros.

Intense vehicle traffic is one of the main disorders in large cities, and in Brazil, where the responsible authorities have not trained the road networks, overcrowding in traffic causes even more obstacles. The applications of computational intelligence techniques in traffic are very broad, with emphasis on smart traffic lights. For the design of intelligent traffic lights, this work proposes the use of Fuzzy Logic, and has as main objective the automatic generation of fuzzy systems using evolutionary fuzzy models for this purpose. To achieve this objective, the traffic simulation software SUMO is used, which allows the elaboration of scenarios of intersections controlled by traffic lights. In these scenarios, the traffic performance is evaluated based on different adjustments in the membership functions and in the set of rules of the fuzzy system that controls the traffic lights, and these adjustments are performed by Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). When comparing the traffic performance with traffic lights controlled by fuzzy and fuzzy with optimized hyperparameters, there are important improvements in the analyzed traffic variables, such as waiting time and car queue size/length, in addition to reducing the emission of toxic gases and fuel consumption. Thus, this work highlights the importance of employing evolutionary fuzzy models in hyperparameters optimization.