<![CDATA[Delivery of goods using two-wheeled vehicles is a dominant model of logistical distribution in urban areas of Indonesia, yet it faces practical challenges such as limited load capacity, traffic congestion, and adverse weather conditions. This study develops a model of the Capacitated Vehicle Routing Problem with Pickup and Delivery (CVRPPD) based on the Particle Swarm Optimization (PSO) algorithm to generate optimal routes that are both efficient and adaptive to these constraints. The model utilizes customer spatial data, shipment loads (both delivery and pickup), and environmental penalty factors in the form of weather and traffic levels, represented on an ordinal scale. The simulation process was executed over 200 iterations, yielding the best solution at iteration 60 with a best cost value of 2554.84 and a total of 13 vehicle routes, each complying with the maximum load capacity of 20 kg. The results indicate that PSO is capable of generating balanced, efficient, and realistic route allocations by explicitly accounting for the operational challenges faced by couriers in the field. This study contributes to the development of data-driven and AI-based logistics optimization systems that are contextualized for urban environments in developing countries.]]>
Copyrights © 2025
