Validation of Trade-Off in Human–Automation Interaction: An Empirical Study of Contrasting Office Automation Effects on Task Performance and Workload

Abstract

Automation aims to improve the task performance and the safety of human operators. The success of automation can be facilitated with well-designed human-automation interaction (HAI), which includes the consideration of a trade-off between the benefits of reliable automation and the cost of Failed automation. This study evaluated four different types of HAIs in order to validate the automation trade-off, and HAI types were configured by the levels and the statuses of office automation. The levels of automation were determined by information amount (i.e., Low and High), and the statues were decided by automation function (i.e., Routine and Failed). Task performance including task completion time and accuracy and subjective workload of participants were measured in the evaluation of the HAIs. Relatively better task performance (short task completion time and high accuracy) were presented in the High level in Routine automation, while no significant effects of automation level were reported in Failed automation. The subjective workload by the National Aeronautics and Space Administration (NASA) Task Load Index (TLX) showed higher workload in High and Failed automation than Low and Failed automation. The type of sub-functions and the task classification can be estimated as major causes of automation trade-off, and dissimilar results between empirical and subjective measures need to be considered in the design of effective HAI. the amount of automation autonomy and human physical and cognitive activity [5,6]. Sheridan and Verplank [7] suggested 10 LOA as the basis of the classic human-machine task allocation principle: at a higher level, automation can execute decision-making tasks without the aid of human operators, at a lower level, it can execute an option within the operators' controls, and at a further lower level, it may be simply performed by the human operators. Kaber and Endsley [6] proposed that automation could be classified according to the information-processing stages: perceiving the status of the system variables or scanning displays (i.e., monitoring), formulation of task-processing plans (i.e., generating), deciding on an optimal plan (i.e., selecting), and the control actions at an interface (i.e., implementing). Elaborating on this classification, Parasuraman et. al. [4] presented a four-stage model of automation to support the design of human-automation interactions (HAI) in complex systems: information acquisition, information analysis, decision and action selection, and action implementation. This classification aids the formulation of specific function allocation schemes for automation. The combination of the LOA with information processing stages led to the development of a concept known as the degree of automation (DOA) [3]. Each function in a model or an information processing stage, either by the human or machine (or some combination thereof), is responsible for the effects of automation on the task performance.Under routine conditions or at higher LOA or DOA, human operators simply supervi...

User Stress in Artificial Intelligence: Modeling in Case of System Failure

“…2) APPARATUS A previous program developed using Visual Studio C# (Visual Studio 2015, Microsoft Co., USA) was applied to conduct the experiment [33], [34]. The program included four different auto-proofreading sessions (i.e., sessions A, B, C, and D) [9]: Session A: A reliable auto-proofreading condition indicating a grammatical error with an underline and without providing a suggestion (word).…”

Identifying essential skills and competencies towards building a training framework for future operators of autonomous ships: a qualitative study

“…YARA Birkeland) with the purpose to decongest roads and provide more sustainable shipping (Emad, Enshaei & Ghosh 2021, Deling et al 2020Munim 2019;Rødseth & Nordahl 2017). However, although valuable but, the automation systems can pose challenges and have negative consequences on human performance (Lee, Park, Jeong et al 2020). This is mainly because the systems are designed and operated by humans and hence liable to create mistakes or fail occasionally.…”