Abstract
Supervisory control of multiple autonomous vehicles raises many issues concerning the balance of system autonomy with human interaction for optimal operator situation awareness and system performance. An unmanned vehicle simulation designed to manipulate the application of automation was used to evaluate participants’ performance on image analysis tasks under two automation conditions: static (level of automation remained constant throughout trials) and adaptive (level of automation adapted as a function of performance on five types of tasks). The results showed that performance-based adaptation of the image task autonomy level improved performance on this task, as well as other tasks. Additionally, participants preferred the adaptive automation condition and felt that it reduced their cognitive workload and aided performance. Research issues are identified to further evaluate performance-based adaptation for supervisory control.
Get full access to this article
View all access options for this article.