Internet of Things (IoT) is novel pattern which is giving immeasurable services. Several applications integrate physical objects by internet as well as transmit data gathered over network without human interference. Artificial Intelligence (AI) is the potentiality of a machine to carry out analytical consequences like, assessing, inferring, learning and problem-solving that humans are competent of carrying out at ease. Nevertheless, there still remains scope to IoT in transportation (i.e., Internet of Transportation things) where AI benefits from Intelligent Transportation Systems (ITS). This is owing to the reason that with the immense growth in population has resulted in increase in demand for vehicles. This has inspired several researchers to come up with numerous features by designing pertinent applications to make transportation smart by optimization vehicle route, ensuring smooth and smart parking, therefore paving ways and mechanisms in reducing congestions and accidents. In this work to circumvent traffic jams as well as solve congestion problems, Radial Basis Interpolated Neural Network and Quantum Finite Automata (RBINN-QFA) route optimization technique is applied to identify optimal route. Sensors positioned on each of the junctions are used to collect data at different time. A Radial Basis Interpolated Neural Network (RBI-NN) algorithm is first applied to identify the arrival time of vehicles for data allocation. Next, Quantum Finite Automata (QFA) is applied for group routing so which traffic congestion is reduced. Grouping here are formed based on the number of vehicles and junction. The Quantum Finite Automata algorithm assigned routes to vehicles to evade congestion and therefore ensuring optimized vehicle routing. Simulation outcomes represent that RBINN-QFA method give high routing accuracy as well as minimum route detection time with improved sensitivity and specificity.