Artificial Intelligence-Driven Ant Colony Optimization for Sustainable Food Delivery and Carbon Footprint Reduction

The rapidly expanding urban food delivery industry has raised environmental concerns due to carbon emissions, delivery delays, and increased operating expenses. This study proposes an Artificial Intelligence-driven system that integrates Ant Colony Optimization (ACO) with carbon emission tracking to enhance route planning for sustainable food delivery. By developing environmentally friendly and effective delivery routes, the main objective is to decrease fuel usage, reduce delivery delays, and lower the overall carbon footprint. The system uses the Haversine formula and vehicle-specific emission factors to generate optimum routes and predicted carbon emissions based on delivery locations entered by customers through a Streamlit-based web application. ACO, inspired by the foraging behavior of ants, finds the quickest and least polluting routes by dynamically updating pheromone trails based on route distances. Compared to traditional algorithms, the model uses real-time traffic data to dynamically adjust routes, which reduces delivery times by 19%, fuel consumption by 13%, and carbon emissions by 14%. The proposed solution demonstrates how AI, coupled with nature-inspired optimization, may greatly improve urban logistics while advancing environmental sustainability.