Intelligent Multi-Objective Optimization for UAV Mission Decision Support

Abstract

Solar-powered Unmanned Aerial Vehicles (UAVs) and High-Altitude Pseudo-Satellites (HAPS) offer significant potential for persistent intelligence, surveillance and reconnaissance operations, but their endurance remains constrained by variable solar irradiance, atmospheric turbulence, battery limitations and payload power demand. This review examines the role of Artificial Intelligence (AI) and Machine Learning (ML) in improving UAV decision-support optimization through predictive solar forecasting, reinforcement-learning-based flight-path optimization, adaptive Maximum Power Point Tracking (MPPT), battery state estimation and intelligent payload load balancing. The paper synthesizes current approaches using Long Short-Term Memory networks, gradient-boosting models, convolutional neural networks, graph neural networks and reinforcement learning architectures for autonomous energy-aware flight. Simulation-based analyses suggest that AI-assisted control can improve energy utilization by 15-25% and extend mission persistence by 30-40%, particularly under variable irradiance and wind conditions. However, practical deployment requires robust validation, certifiable AI architectures, adversarial resilience and reliable edge-computing implementation. The strategic deployment of AI-enabled autonomous UAVs directly supports Saudi Arabia's Vision 2030 objectives for indigenous defence technology development, artificial intelligence research, and advanced aerospace systems. By establishing domestic expertise in AI-driven decision-support optimization, the Kingdom advances its defence industrial sovereignty while creating high-value technical employment in autonomous systems engineering and aerospace artificial intelligence.