Optimizing Aerial Surveying Operations with an Adaptive MDP-Based Scheduling Model for Single Aircraft

Abstract

This study introduces a dynamic scheduling model for single-aircraft aerial surveying, designed to maximize productivity while managing various operational costs effectively. Utilizing the Markov Decision Process (MDP) framework, the model enables adaptive decision-making, allowing the aircraft to select actions such as surveying, idling, or relocating in response to real-time environmental and operational conditions. By accommodating uncertainties in weather, the model aligns actions with the objective of maximizing productivity at minimal cost. The methodology simplifies complex scheduling tasks by applying structured decision-making to adapt to unpredictable conditions, optimizing resource allocation to high-priority tasks. Our findings demonstrate that this adaptive model provides a robust solution for decision-making under uncertainty, proving especially valuable in environments with dynamic operational conditions. Additionally, this approach not only maximizes immediate productivity but also lays the groundwork for future extensions to fleet-based aerial surveying using multi-agent MDPs. The research implications extend to enhanced logistics and resource management within dynamic, demand-driven settings under uncertainty, offering a scalable and versatile method for optimizing aerial surveying operations across diverse conditions.