An Optimization Framework for Automated and Human-Operated Fleet Routing

This paper presents a mathematical model to determine the optimal routes for a heterogeneous fleet comprising autonomous and human-driven vehicles operating in freight distribution. The model is formulated as a mixed-integer programming problem with multiple objectives: minimize total emissions, energy consumption, and operational costs, while maximizing the reliability associated with autonomous vehicle deployment. A dedicated parameter models the probability that an autonomous vehicle can successfully traverse a given arc, enforcing a minimum reliability threshold. The proposed optimization framework is embedded within a higher-level decision support system that enables route adjustments based on discrete-time monitoring of network reliability conditions. Since the multi-objective model is solved by means of scalarization, a specific algorithm is designed to adjust the weights of the objectives. A case study is provided to demonstrate the effectiveness of the model and its practical applicability. To further enhance the performance of the proposed model in solving larger instances, three families of valid inequalities are presented, and a computational comparison between the basic model and the improved model is shown in a single-objective environment (operational cost minimization). We also implement a constructive heuristic and an Adaptive Large Neighborhood Search metaheuristic to further appreciate the reduced duality gaps achieved by the enhanced model.