GUI Interaction on Autopilot
Christina Chung, Mohammad Kianpisheh, Sahand Akbari
Undertaken as a part of the human-computer interaction course (CSC428) at the University of Toronto. The paper received a grade of 130%.
ABSTRACT
By making objects tangible and directly manipulable, graphical user interfaces make it easy for non-programmers to operate a computer. But because these interfaces suffer from an inherent lack of programmability, users are often subjected to the tedium of manually repeating their tasks. We propose Autopilot, a context-aware system that detects and automates repetitive behavior. Our evaluation of Autopilot, against the baseline of manual input, shows that the system substantially reduces the amount of time it takes for participants to perform repetitive tasks.
A link to the full PDF version is available here.