Principles for ‘intelligent assistant’ systems in future flight deck design: autonomous action integration to reduce pilot workload

Abstract

The introduction of advanced automation and human-artificial intelligence (AI) teaming is expected to permit more efficient use of airspace in the face of increasing air transport demand. Additionally, the development of next-generation aircraft to support net-zero has introduced more complexity into the future flight deck and informational requirements. This study evaluates a design for an ‘intelligent assistant’ system that could share tasks with the pilot during engine failure and pilot incapacitation events, promoting greater reliance on system interaction as workload increases. Four professional pilots were split into two groups to perform six and eight scenarios, respectively. The aim was to identify the task-related information for the designed system to promote transparency to the pilots. Three modalities varied across each scenario (visual, auditory and physical) to evaluate the combination of modality to increase pilot monitoring and interaction with the system. Analysis of participant feedback indicated key limitations to existing human-machine-interaction design, with current operational procedures creating disparity between the system and pilots’ authority to handle the scenario. Additionally, the use of audio narration was negatively received by participants, primarily due to the potential overlap between other audio stimuli, masking the perception of task-critical audio prompts and delaying critical flight tasks from being performed. Design considerations were generated for future ‘intelligent assistant’ systems, with further research required to understand the effect of each modality on pilot reliance on these ‘intelligent assistant’ systems.