Machine Learning Prediction Based UI for Aircraft Cockpit

Pilot vehicle interfaces on aircraft, similar to the automobile digital displays found in automobiles, are used to present the current status of various systems (e.g., navigation, engine information). Aircraft interfaces exhibit deterministic behavior due to safety concerns, ensuring that user input yields predictable outputs. Consequently, integrating text-based pattern recognition or artificial neural network based solutions to aircraft systems are challenging because of their deterministic nature. In this paper, an approach complementary to the existing user interface models is proposed. This approach is based on learning recurring user interactions during flight. It utilizes text-based pattern recognition and prediction models based on user interaction logs and sensor readings. Test results on sample data suggest that the proposed approach yields faster and context-aware user interaction model that decreases the time needed to perform tasks in the aircraft cockpit, where timing is crucial.