Coordinated Optimization of Inter-Hub eVTOL Feeder Services with Heterogeneous Passenger Behavior

Inter-hub feeder service is a promising application for electric vertical takeoff and landing aircraft (eVTOL), especially for passengers connecting to subsequent flights under tight time constraints. We develop an optimization framework that accounts for heterogeneous passenger behavior. Using stated-preference survey data, we incorporate delay-risk perception under remaining connection time constraints, identify heterogeneous preference classes, and formulate a bilevel optimization model. The upper level selects eVTOL schedules under given resource and fare configurations. The lower level captures the stochastic user equilibrium of heterogeneous passengers choosing among eVTOL and external transport alternatives. To solve the resulting mixed-integer nonlinear bilevel problem, we propose a Neural Bilevel Optimization and generalized Benders decomposition (Neur2BiLO-GBD) hybrid algorithm. Numerical experiments on the Shanghai Hongqiao–Pudong corridor show that the baseline profit-maximizing plan also generates positive social net utility for the feeder system. Fleet size, charging infrastructure, and fare affect operator profit and social net utility differently, so their high-value regions do not fully coincide. When external transport has larger potential delays and remaining connection time is short, eVTOL is more likely to achieve both high operator profit and high social net utility.