Artificial Intelligence Techniques for Autonomous UAV Navigation: A Comprehensive Review of Perception, Path Planning, and Motion Control

Abstract

This review provides a comprehensive synthesis of traditional and artificial intelligence (AI)-based techniques across the complete autonomous UAV navigation pipeline, including environmental perception, localization and mapping, path planning and obstacle avoidance, and motion control. It systematically examines recent advances in computer vision, SLAM, deep reinforcement learning, transformer-based methods, multimodal sensor fusion, and intelligent control, together with commonly used datasets, simulation platforms, and evaluation practices. The comparative analysis identifies hybrid AI architectures as the most promising direction for practical autonomous UAV navigation, as they combine the reliability and interpretability of conventional navigation methods with the adaptability and learning capabilities of AI-based approaches. The review further identifies computational and energy constraints, safety and explainability, robust multimodal sensor fusion, cybersecurity, and simulation-to-real transfer as major barriers to large-scale real-world deployment. Emerging technologies, including foundation models, vision-language models, edge AI, federated learning, digital twins, and swarm intelligence, are also examined as potential enablers of next-generation UAV autonomy. By integrating these findings across perception, localization, planning, and control within a unified framework, this review clarifies the current technological trade-offs, highlights the key barriers to real-world deployment, and provides specific research priorities for developing safe, adaptive, computationally efficient, and scalable autonomous UAV navigation systems.