Integration of Commuter Carpooling Pricing and Multi-Objective Matching for Optimization Using an Improved Genetic Algorithm Based on Open-Ended Mileage Initialization

This study addresses the multiconstraint matching problem in commuter carpooling systems and develops a multi-objective optimization model that incorporates capacity limits, time window deviations, and detour tolerance constraints. An improved genetic algorithm based on the concept of open-ended saving-mileage, referred to as GAOSA, is proposed. In the mathematical modeling stage, the spatial positions of commuters are represented through two-dimensional coordinates, and feasible matching relations are established by combining arrival times with time window constraints. The fitness function is designed to reduce total driving distance and increase the matching rate. To enhance search efficiency and avoid premature convergence caused by random initialization in traditional genetic algorithms, GAOSA constructs a heuristic initial solution according to saving potential and then performs selection, crossover, and mutation to iteratively improve the matching solution. Small-scale randomly generated instances are used for experimental validation. The results show that GAOSA reduces average travel distance and accelerates convergence while maintaining the same matching rate. The method establishes an executable matching framework under spatial, temporal, and behavioral constraints and provides a computational strategy for scheduling and resource coordination in commuter carpooling systems.