Predictive Analytics for Modeling UAS Safety Risk

Abstract

This paper illustrates the development of an Object-Oriented Bayesian Network (OOBN) to integrate the safety risks contributing to a notional “lost link” scenario for a small UAS (sUAS). This hypothetical case investigates the possibility of a “lost link” for the sUAS during the bridge inspection mission leading to a collision of the sUAS with the bridge. Hazard causal factors associated with the air vehicle, operations, airmen and the environment may be combined in an integrative safety risk model. With the creation of a probabilistic risk model, inferences about changes to the states of the mishap shaping or causal factors can be drawn quantitatively. These predictive safety inferences derive from qualitative reasoning to conclusions based on data, assumptions, and/or premises and enable an analyst to identify the most prominent causal factor clusters. Such an approach also supports a mitigation portfolio study and assessment. An OOBN approach facilitates decomposition at the subsystem level yet enables synthesis at a higher-order systems level. It is essentially a System of Systems (SoS) approach that fosters the integration of sub-nets of risk factors. Such a study provides insight into the integration of UAS into the National Airspace System (NAS) that may be used to eventually inform type design, airworthiness, certifications, safety analyses and risk assessments, and operational requirements.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 7 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.