Adaptive Automation and Human Performance: 1. Multi-Task Performance Characteristics

1992 ◽  
Author(s):  
Raja Parasuraman ◽  
Toufik Bahri ◽  
Robert Molloy
Keyword(s):  
Task Performance ◽  
Human Performance ◽  
Performance Characteristics ◽  
Adaptive Automation

scholarly journals Beneficial and harmful explanatory machine learning

2021 ◽  
Author(s):  
Lun Ai ◽  
Stephen H. Muggleton ◽  
Céline Hocquette ◽  
Mark Gromowski ◽  
Ute Schmid
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Beneficial Effect ◽  
Empirical Evidence ◽  
Task Performance ◽  
Human Performance ◽  
Human Learning ◽  
Science Literature ◽  
Definition Of ◽  
Self Learning

AbstractGiven the recent successes of Deep Learning in AI there has been increased interest in the role and need for explanations in machine learned theories. A distinct notion in this context is that of Michie’s definition of ultra-strong machine learning (USML). USML is demonstrated by a measurable increase in human performance of a task following provision to the human of a symbolic machine learned theory for task performance. A recent paper demonstrates the beneficial effect of a machine learned logic theory for a classification task, yet no existing work to our knowledge has examined the potential harmfulness of machine’s involvement for human comprehension during learning. This paper investigates the explanatory effects of a machine learned theory in the context of simple two person games and proposes a framework for identifying the harmfulness of machine explanations based on the Cognitive Science literature. The approach involves a cognitive window consisting of two quantifiable bounds and it is supported by empirical evidence collected from human trials. Our quantitative and qualitative results indicate that human learning aided by a symbolic machine learned theory which satisfies a cognitive window has achieved significantly higher performance than human self learning. Results also demonstrate that human learning aided by a symbolic machine learned theory that fails to satisfy this window leads to significantly worse performance than unaided human learning.

scholarly journals Initiators and Triggering Conditions for Adaptive Automation in Advanced Small Modular Reactors

2014 ◽  
Author(s):  
Katya L. Le Blanc ◽  
Johanna H. Oxstrand
Keyword(s):  
Situation Awareness ◽  
System Performance ◽  
Human Performance ◽  
Hybrid Methods ◽  
Empirical Literature ◽  
Physiological Measurement ◽  
Adaptive Automation ◽  
Small Modular Reactors ◽  
Levels Of Automation ◽  
Triggering Mechanisms

It is anticipated that Advanced Small Modular Reactors (AdvSMRs) will employ high degrees of automation. High levels of automation can enhance system performance, but often at the cost of reduced human performance. Automation can lead to human out-of the loop issues, unbalanced workload, complacency, and other problems if it is not designed properly. Researchers have proposed adaptive automation (defined as dynamic or flexible allocation of functions) as a way to get the benefits of higher levels of automation without the human performance costs. Adaptive automation has the potential to balance operator workload and enhance operator situation awareness by allocating functions to the operators in a way that is sensitive to overall workload and capabilities at the time of operation. However, there still a number of questions regarding how to effectively design adaptive automation to achieve that potential. One of those questions is related to how to initiate (or trigger) a shift in automation in order to provide maximal sensitivity to operator needs without introducing undesirable consequences (such as unpredictable mode changes). Several triggering mechanisms for shifts in adaptive automation have been proposed including: operator initiated, critical events, performance-based, physiological measurement, model-based, and hybrid methods. As part of a larger project to develop design guidance for human-automation collaboration in AdvSMRs, researchers at Idaho National Laboratory have investigated the effectiveness and applicability of each of these triggering mechanisms in the context of AdvSMR. Researchers reviewed the empirical literature on adaptive automation and assessed each triggering mechanism based on the human-system performance consequences of employing that mechanism. Researchers also assessed the practicality and feasibility of using the mechanism in the context of an AdvSMR control room. Results indicate that there are tradeoffs associated with each mechanism, but that some are more applicable to the AdvSMR domain than others. The two mechanisms that consistently improve performance in laboratory studies are operator initiated adaptive automation based on hierarchical task delegation and the Electroencephalogram (EEG)–based measure of engagement. Current EEG methods are intrusive and require intensive analysis; therefore it is not recommended for an AdvSMR control rooms at this time. Researchers also discuss limitations in the existing empirical literature and make recommendations for further research.

Computational GOMSL Modeling towards Understanding Cognitive Strategy in Dual-Task Performance with Automation

2007 ◽  
Vol 51 (12) ◽  
pp. 802-806
Author(s):  
Sang-Hwan Kim ◽  
David B. Kaber ◽  
Carlene M. Perry
Keyword(s):  
Task Performance ◽  
Dual Task ◽  
Cognitive Modeling ◽  
Adaptive Systems ◽  
Human Performance ◽  
Automated System ◽  
Control Mode ◽  
Manual Control ◽  
Dual Task Performance ◽  
Mode Transitions

The objective of this study was to assess the use of a computational cognitive model for describing human performance with an adaptively automated system, with and without advance cueing of control mode transitions. A dual-task piloting simulation was developed to collect human performance data under auditory cueing or no cueing of automated or manual control. GOMSL models for simulating user behavior were constructed based on a theory of increased memory transactions at mode transitions. The models were applied to the same task simulation and scenarios performed by the humans. Comparison of results on human and model output demonstrated the model to be generally descriptive of performance; however, it was not accurate in predicting timing of memory use in preparing for manual control. Interestingly, the human data didn't reveal differences between cued and no cue trials. A refined GOMSL model was developed by modifying assumptions on the timing and manner of memory use, and considering human parallel processing in dual-task performance. Results revealed the refined model to be more plausible for representing behavior. Computational cognitive modeling appears to be a viable approach to represent operator performance in adaptive systems.

scholarly journals Regulation of arousal via online neurofeedback improves human performance in a demanding sensory-motor task

2019 ◽  
Vol 116 (13) ◽  
pp. 6482-6490 ◽  
Author(s):  
Josef Faller ◽  
Jennifer Cummings ◽  
Sameer Saproo ◽  
Paul Sajda
Keyword(s):  
Task Performance ◽  
Human Performance ◽  
Motor Task ◽  
Avoidance Task ◽  
Arousal State ◽  
Sensory Motor ◽  
The Subject ◽  
Improved Performance ◽  
The Right ◽  
Bci System

Our state of arousal can significantly affect our ability to make optimal decisions, judgments, and actions in real-world dynamic environments. The Yerkes–Dodson law, which posits an inverse-U relationship between arousal and task performance, suggests that there is a state of arousal that is optimal for behavioral performance in a given task. Here we show that we can use online neurofeedback to shift an individual’s arousal from the right side of the Yerkes–Dodson curve to the left toward a state of improved performance. Specifically, we use a brain–computer interface (BCI) that uses information in the EEG to generate a neurofeedback signal that dynamically adjusts an individual’s arousal state when they are engaged in a boundary-avoidance task (BAT). The BAT is a demanding sensory-motor task paradigm that we implement as an aerial navigation task in virtual reality and which creates cognitive conditions that escalate arousal and quickly results in task failure (e.g., missing or crashing into the boundary). We demonstrate that task performance, measured as time and distance over which the subject can navigate before failure, is significantly increased when veridical neurofeedback is provided. Simultaneous measurements of pupil dilation and heart-rate variability show that the neurofeedback indeed reduces arousal. Our work demonstrates a BCI system that uses online neurofeedback to shift arousal state and increase task performance in accordance with the Yerkes–Dodson law.

Human Performance of Novice Schedulers for Complex Spaceflight Operations Timelines

2021 ◽  
pp. 001872082110589
Author(s):  
Jessica J. Marquez ◽  
Tamsyn Edwards ◽  
John A. Karasinski ◽  
Candice N. Lee ◽  
Megan C. Shyr ◽  
...  
Keyword(s):  
Task Performance ◽  
Situation Awareness ◽  
Human Performance ◽  
Task Complexity ◽  
Lower Number ◽  
Scheduling Problems ◽  
Within Subjects ◽  
Complex Constraints ◽  
Design Scheduling ◽  
Main Effects

Objective Investigate the effects of scheduling task complexity on human performance for novice schedulers creating spaceflight timelines. Background Future astronauts will be expected to self-schedule, yet will not be experts in creating timelines that meet the complex constraints inherent to spaceflight operations. Method Conducted a within-subjects experiment to evaluate scheduling task performance in terms of scheduling efficiency, effectiveness, workload, and situation awareness while manipulating scheduling task complexity according to the number of constraints and type of constraints. Results Each participant ( n = 15) completed a set of scheduling problems. Results showed main effects of the number of constraints and type of constraint on efficiency, effectiveness, and workload. Significant interactions were observed in situation awareness and workload for certain types of constraints. Results also suggest that a lower number of constraints may be manageable by novice schedulers when compared to scheduling activities without constraints. Conclusion Results suggest that novice schedulers' performance decreases with a high number of constraints, and future scheduling aids may need to target a specific type of constraint. Application Knowledge on the effect of scheduling task complexity will help design scheduling systems that will enable self-scheduling for future astronauts. It will also inform other domains that conduct complex scheduling, such as nursing and manufacturing.

Controlling for Individual Differences in a Dual-Task Setting: Equating the Baselines of Single Task Performance

2001 ◽  
Vol 45 (13) ◽  
pp. 916-920
Author(s):  
Bradley Chase ◽  
Holly M. Irwin-Chase ◽  
Jaclyn T. Sonico
Keyword(s):  
Individual Differences ◽  
Task Performance ◽  
Stimulus Duration ◽  
Dual Task ◽  
Secondary Task ◽  
Human Performance ◽  
Visual Task ◽  
Primary Task ◽  
Individual Participant ◽  
The Individual

Individual differences in human performance is an issue that confounds many studies and has not been properly controlled in the ergonomics/human factors literature. This paper examines the concept of individual differences in performance primarily from the perspective of cognitive performance. A study was designed to test the effect of a secondary visual task on a primary visual task. In one condition, participants performed the dual task, while assigning no weight to the secondary task. In the second condition, the primary task was performed simultaneously with the secondary task. The effect of the added workload was measured via the effect on primary task performance. In the baseline portion of the task participants had their baseline (80–90% accuracy) of performance collected by adjusting the stimulus duration. The individual participant stimulus duration was then used as the experimental stimulus duration and the effect of secondary task performance on primary task performance was measured.

The effect of dynamic correlated colour temperature changes on alertness and performance

2018 ◽  
Vol 50 (7) ◽  
pp. 1070-1081 ◽  
Author(s):  
M Ye ◽  
SQ Zheng ◽  
ML Wang ◽  
M Ronnier Luo
Keyword(s):  
Task Performance ◽  
Human Performance ◽  
Temperature Cycle ◽  
Acute Effects ◽  
Temperature Changes ◽  
Colour Temperature ◽  
Cycle Times ◽  
Circadian Phase ◽  
And Performance ◽  
And Task

Light can have acute effects on human performance, including task performance, alertness and circadian phase shift. Most studies have investigated these effects using static light. This study investigates the effects of dynamic light with different cycle times and different ranges of correlated colour temperature on human alertness and task performance. Ten participants took part in the experiment using six conditions of dynamic light with each observing session lasting 4.5 hours. An electroencephelogram, measurements of critical flicker frequency, performance on various cognitive tasks and alertness and sleepiness questionnaires were used to evaluate the human responses. The results showed that participants appeared more alert and performed better under lighting of higher correlated colour temperature range but different correlated colour temperature cycle times had little effect.

scholarly journals Improving Human Performance in Dynamic Tasks with Debriefing-Based Interactive Learning Environments: An Empirical Investigation

2020 ◽  
Vol 19 (04) ◽  
pp. 1065-1089
Author(s):  
Hassan Qudrat-Ullah
Keyword(s):  
Decision Making ◽  
Task Performance ◽  
Human Performance ◽  
Interactive Learning ◽  
Decision Time ◽  
Decision Strategy ◽  
Interactive Learning Environment ◽  
Ongoing Research ◽  
Dynamic Task ◽  
Process Oriented

Dynamic tasks are pervasive in organizational decision making. Improving managerial performance in dynamic tasks is an ongoing research endeavor. We report a laboratory experiment in which participants managed a dynamic task by playing the roles of fishing fleet managers. The two experimental groups used a computer simulation-based interactive learning environment (ILE) with an outcome-oriented debriefing and a process-oriented debriefing. To assess the users’ learning and performance, a comprehensive five-dimensional model was used to evaluate subjects’ task performance, decision time, decision strategy, structural knowledge, and heuristics knowledge. The results showed that process-oriented debriefing improved subjects’ task performance, helped users gain task knowledge, develop heuristics, and adapt to systematic-variable consistent strategies. Contrary to our hypothesis, the process-oriented debriefing group did not use less decision time. In contrast to the cost-benefit approach to decision making, a relatively more systematic effort is needed to perform better in dynamic tasks such as fisheries management.

Sign in / Sign up

Export Citation Format

Share Document