Dependability of UAV-Based Networks and Computing Systems: A Survey

2025-06-20

AI Summary

To address the insufficient dependability of unmanned aerial vehicle (UAV) networks and computing systems under multi-source uncertainties—including software defects, hardware failures, communication disruptions, energy constraints, and environmental interference—this study conducts a systematic literature review (SLR). It introduces, for the first time, a two-dimensional dependability classification framework tailored to UAV systems, organized along threat types and technical mitigation pathways, and systematically synthesizes existing approaches. The work identifies eight key research directions and consolidates a comprehensive technical taxonomy encompassing fault tolerance, self-healing mechanisms, resilient resource scheduling, and AI-enhanced trustworthiness. These contributions establish a theoretical foundation and evolutionary roadmap for developing highly dependable space-air-ground integrated computing systems.

Technology Category

• Multiagent Systems: Multiagent Systems under Uncertainty
• Reasoning under Uncertainty: Uncertainty Representations
• Planning, Routing, and Scheduling: Planning under Uncertainty

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

Uncrewed Aerial Vehicle (UAV) computing and networking are becoming a fundamental computation infrastructure for diverse cyber-physical application systems. UAVs can be empowered by AI on edge devices and can communicate with other UAVs and ground stations via wireless communication networks. Dynamic computation demands and heterogeneous computing resources are distributed in the system and need to be controlled to maintain the quality of services and to accomplish critical missions. With the evolution of UAV-based systems, dependability assurance of such systems emerges as a crucial challenge. UAV-based systems confront diverse sources of uncertainty that may threaten their dependability, such as software bugs, component failures, network disconnections, battery shortages, and disturbances from the real world. In this paper, we conduct systematic literature reviews on the dependability of UAV-based networks and computing systems. The survey report reveals emerging research trends in this field and summarizes the literature into comprehensive categories by threat types and adopted technologies. Based on our literature reviews, we identify eight research fields that require further exploration in the future to achieve dependable UAV-based systems.

Problem

• Ensuring dependability in UAV-based networks and computing systems
• Managing dynamic computation demands and heterogeneous resources
• Addressing uncertainties like failures and disruptions in UAV systems

Innovation

• AI-powered edge devices for UAV computing
• Dynamic resource control for service quality
• Systematic dependability review for UAV networks