UAVs Meet Agentic AI: A Multidomain Survey of Autonomous Aerial Intelligence and Agentic UAVs

2025-06-08

AI Summary

Current autonomous UAVs lack goal-directed behavior, contextual reasoning, and interactive autonomy in complex real-world environments, hindering integrated perception, decision-making, memory, and collaborative planning. Method: This work introduces the novel concept of “Agentic UAVs”—embodied intelligent autonomous systems—and systematically defines their distinguishing characteristics relative to conventional autonomous platforms. We establish a comprehensive Agentic AI technical architecture encompassing multimodal sensing, online reinforcement learning, distributed collaborative reasoning, and explainable human–UAV interaction, synergistically integrating edge-intelligent hardware and federated learning frameworks. Contribution/Results: We propose cross-domain application pathways across seven critical sectors—including agriculture, disaster response, and logistics—alongside a vision for self-evolving aerial ecosystems and a human–UAV co-evolution roadmap. Furthermore, we identify three fundamental technical challenges and formulate a technology–policy co-governance framework, establishing an international benchmark for the research, deployment, and governance of Agentic UAVs.

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Intelligent Robots: Embodied AI
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Agentic UAVs represent a new frontier in autonomous aerial intelligence, integrating perception, decision-making, memory, and collaborative planning to operate adaptively in complex, real-world environments. Driven by recent advances in Agentic AI, these systems surpass traditional UAVs by exhibiting goal-driven behavior, contextual reasoning, and interactive autonomy. We provide a comprehensive foundation for understanding the architectural components and enabling technologies that distinguish Agentic UAVs from traditional autonomous UAVs. Furthermore, a detailed comparative analysis highlights advancements in autonomy with AI agents, learning, and mission flexibility. This study explores seven high-impact application domains precision agriculture, construction&mining, disaster response, environmental monitoring, infrastructure inspection, logistics, security, and wildlife conservation, illustrating the broad societal value of agentic aerial intelligence. Furthermore, we identify key challenges in technical constraints, regulatory limitations, and data-model reliability, and we present emerging solutions across hardware innovation, learning architectures, and human-AI interaction. Finally, a future roadmap is proposed, outlining pathways toward self-evolving aerial ecosystems, system-level collaboration, and sustainable, equitable deployments. This survey establishes a foundational framework for the future development, deployment, and governance of agentic aerial systems (Agentic UAVs) across diverse societal and industrial domains.

Problem

• Exploring autonomous UAVs with AI-driven perception and decision-making
• Comparing Agentic UAVs' advancements in AI and mission flexibility
• Addressing challenges in regulations and data reliability for UAVs

Innovation

• Integrates perception, decision-making, and collaborative planning
• Exhibits goal-driven behavior and contextual reasoning
• Advances in autonomy with AI agents and learning