OLIVIA (OperationaL Intentions adVIser for Aviation) was developed in the HAIKU project. It is a flight deck tool providing support to mission-level decisions in complex situations by assessing and prioritizing route options according to operational intentions. It uses Artificial Intelligence to translate (1) operational intentions from pilots to route generation and optimization inputs and (2) route proposal KPIs into operational intention assessments. This paper reports on the final development of OLIVIA, the results from the human-in-the-loop experiments, and insights and recommendations regarding the development of similar assistants for the flight deck.

Single-Pilot Operations (SPO) in commercial aviation raise critical safety challenges in complex, time-pressured situations where human expertise is paramount. This study investigates how AI-based Human-Autonomy Teaming (HAT) can support pilot decision-making under high workload, compromised situational awareness, and time pressure. In a high-fidelity Airbus A320 simulator, 22 airline pilots performed a fuel- and time-constrained approach scenario designed to challenge HAT’s operational effectiveness under four conditions: no assistance, on-demand AI, proactive AI, and proactive explainable AI. Workload (NASA-TLX) remained high across conditions, yet decision-making differed markedly. Without assistance, only 20% chose the safest landing option; with on-demand AI, 40%; and with proactive AI (both versions), 100%. Explainable AI yielded the highest scenario comprehension (75%), matching two-crew baseline performance. Proactive systems increased decision and SA related interactions, fostering a collaborative dynamic akin to traditional crew resource management. Thus, the results demonstrate that, in the context of SPO, proactive and explainable AI was associated with crew-level decision performance within the experimental scenario without adding cognitive load. Beyond the aeronautical domain, our results are of interest for the design of cognitive support systems for high-risk domains where teams composed of humans and AI must adapt in real time.