An Artificial Intelligence Approach to Enhance the Optimization of the Vehicle Routing Problem

Sustainable development involves an economic plan that prioritizes meeting basic human needs while also taking care of our environment through the use of technology. A key step we can take towards this goal is optimizing our supply chain processes to reduce air pollution and traffic congestion on our planet. This approach benefits all citizens by reducing daily traffic jams. To achieve this, we are focused on solving the vehicle routing problem (VRP) with time windows and synchronization constraints. Our multi-agent system utilizes genetic and metaheuristic algorithms, such as simulated annealing and the nearest neighbour method, to generate efficient routes for three vehicles in response to customer requests. Our objective is to calculate the total distance for each route and assess the probability of stopping for each vehicle. Through parallel processing, our agents collect and analyze data related to VRP problems for customer locations and classify vehicle data based on their model and type. By utilizing these methods, we can achieve sustainable development while also improving the lives of citizens.