Intelligent Health and Mission Management for UAS-Assisted Wireless Networks

In many types of uncrewed aircraft systems (UAS), commonly occurring faults have the potential to negatively impact the mission or even compromise the safety of flight. The adoption of onboard intelligent health and mission management (IHMM) functionalities is, therefore, essential both to ensure service continuity and to support trusted autonomous flight operations. This article proposes a new IHMM system architecture and associated software functionalities for a UAS-assisted wireless communication service. The proposed system is capable of predicting and early detecting faults affecting relevant UAS subsystems. Such capabilities also support a real-time updating of the mission plan, allowing fast formation reconfiguration and minimizing mission performance degradations. The diagnosis of faults affecting UAS communication subsystems is accomplished using suitably selected machine learning (ML) techniques. A representative case study of a UAS-assisted wireless communication service is used to verify the effectiveness of the proposed techniques. The analysis of network coverage and capacity demonstrates that, in the presence of various failure events, the network maintains an acceptable level of performance by following the IHMM resolutions to reposition the remaining flight vehicles in the formation. The case study also demonstrates how a combination of ML techniques for fault prediction/early detection and metaheuristic algorithms for UAS topology optimization can provide a complete IHMM solution, thereby ensuring a high level of integrity, continuity, availability, and overall mission performance.