The Impact of Skill-based Training Across Different Levels of Autonomy for Drone Inspection Tasks
Given their low operating costs and flight capabilities, Unmanned Aircraft Vehicles(UAVs), especially small size UAVs, have a wide range of applications, from civilian rescue missions to military surveillance. Easy control from a highly automated system has made these compact UAVs particularly efficient and effective devices by alleviating human operator workload. However, whether or not automation can lead to increased performance is not just a matter of system design but requires operators’ thorough understanding of the behavior of the system. Then, a question arises: which type of training and level of automation can help UAV operators perform the best?
To address this problem, an experiment was designed and conducted to compare the differences in performance between 3 groups of UAV operators. For this experiment, 2 different interfaces were first developed - Manual Control, which represents low LOA interface, and Supervisory Control, which represents high LOA interface - and people were recruited and randomly divided into 3 groups. Group 1 was trained using Manual Control, and Group 3 was trained using Supervisory Control while Group 2 was trained using both Manual and Supervisory Control. Participants then flew a drone in the Test Mission stage to compare performance.
The results of the experiment were rather surprising. Although group 3 outperformed group 1, as expected, the poor performance of group 2 was unexpected and gave us new perspectives on additional training. That is, additional training could lead not just to a mere surplus of extra skills but also a degradation of existing skills. An extended work using a more mathematical approach should allow for a more precise, quantitative description on the relation between extra training and performance.
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 United States License.
Rights for Collection: Masters Theses