Wind-Aware RRT* with Neural Energy Refinement for Energy-Efficient Urban Air Mobility

Urban air mobility depends on small aerial vehicles threading through dense, wind-swept cities, yet most sampling-based planners treat the urban wind field as noise to reject rather than structure to exploit—and pay for it in flight energy. We take the opposite view. Behind every building lies a sheltered wake where the air slows and aerodynamic drag drops, and this work turns that physical fact into a planning principle. We present an energy-aware, wind-shadow-aware framework that routes a single quadrotor, at the planning level, through these low-wind corridors. The wind model couples a power-law shear profile with Ekman directional veer and a frozen-turbulence gust component, grounding the planner in realistic boundary-layer physics. A feed-forward neural energy surrogate, trained to approximate a cost field that aggregates wind exposure and obstacle clearance, then guides a two-stage refinement—energy-aware, collision-checked shortcutting followed by Laplacian and energy-guided smoothing—so that every accepted change stays collision-free. Against classical sampling-based baselines (RRT, goal-biased RRT, Informed RRT*, and BIT*) over a 50-run Monte-Carlo study, evaluated with multi-criteria metrics and Pareto-dominance analysis, the framework characterizes how wind-shadow-aware routing balances route energy against smoothness and clearance, offering a reproducible, wind-informed basis for flying robots navigation.