🤖 AI Summary
This study addresses the risks of infeasible energy consumption and failed return flights for drones in low-altitude air-ground collaborative delivery caused by uncertain wind fields. To this end, it proposes the first online risk-sensitive, wind-resilient routing framework. The approach constructs a time-varying directed energy graph that dynamically integrates delayed and noisy wind field estimates, payload states, and conservative uncertainty bounds to model wind-induced propulsion energy consumption and return feasibility in real time. This overcomes the limitations of conventional static or deterministic energy models. Experimental results demonstrate that the framework significantly improves mission success rates and effectively reduces wind-induced return failure rates under realistic wind field replay scenarios.
📝 Abstract
Energy feasibility under wind uncertainty is a critical safety issue for low-altitude air-ground delivery. In truck-UAV systems, UAVs complete assigned deliveries and safely return to a mobile truck or depot, while wind-induced propulsion costs vary online and are only partially observable. Existing routing methods often rely on static or deterministic energy models, which may underestimate headwind, crosswind, battery-voltage, and return-feasibility risks. This paper proposes Energy-Aware Wind-Resilient Routing (EWR), an online risk-sensitive planning framework for wind-aware and energy-safe UAV routing. The delivery environment is represented as a time-dependent directed energy graph whose edge costs are updated using delayed noisy wind estimates, payload states, and conservative uncertainty margins. Experiments using synthetic delivery graphs with replayed wind logs from a public truck-UAV delivery dataset show that EWR improves mission success rates and reduces wind-induced return failures.