Introduction: The rapid rate of urbanization in modern cities is leading to growing operational complexity in Solid Waste Management (SWM), requiring the development of intelligent routing solutions for the sustainable management of urban infrastructure. This study presents an innovative methodological framework that combines a comprehensive analysis of the patent landscape with a comparative evaluation of three metaheuristic algorithms based on Artificial Intelligence (AI), such as the Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Simulated Annealing (SA), to optimize the Multi-Objective Vehicle Routing Problem (MO-VRP). Methods: The research combines an in-depth analysis of patents filed between 2005 and 2024 that reveals major industrial trends in adaptive route optimization, and a synthetic case study was developed to evaluate three metaheuristic algorithms according to three performance indicators, namely total distance traveled, CO2 emissions, and patent-inspired indicator of CO2 per tonne-kilometer (CO2/t·km). Results: The comprehensive analysis of patents highlights major industry trends, including adaptive route optimization, real-time monitoring, and the use of GPS tracking. However, this approach reveals a notable absence of multi-objective environmental optimization. Computational experiments demonstrated that PSO provided the best balance between distance and emissions. Discussion: The results obtained demonstrate the complementary advantages and strengths of metaheuristic algorithms and provide guidance for defining optimization strategies suitable for different municipal deployment scenarios. Conclusion: This work is not limited to a simple comparative analysis. It provides a reproducible simulation framework and outlines concrete areas for innovation in patentable, eco-efficient, and adaptive waste collection systems.
Elasri et al. (Fri,) studied this question.