Predicting Endpoint of Goal-Directed Motion in Modern Desktop Interfaces using Motion Kinematics

Abstract

Researchers who study pointing facilitation have identified the ability to identify--during motion--the likely target of a user's pointing gesture, as a necessary precursor to pointing facilitation in modern computer interfaces. To address this need, we develop and analyze how an understanding of the underlying characteristics of motion can enhance our ability to predict the target or endpoint of a goal-directed movement in graphical user interfaces.

Using established laws of motion and an analysis of users' kinematic profiles, we demonstrate that the initial 90% of motion is primarly balistic and submovements are limited to the last 10% of gesture movement. Through experimentation, we demonstrate that target constraint and the intended use of a target has either a minimal effect on the motion profile or affects the last 10% of motion. Therefore, we demonstrate that any technique that models the intial 90% of gesture motion will not be affected by target constraint or intended use.

Given, these results, we develop a technique to model the initial ballistic motion to predict user endpoint by adopting principles from the minimum jerk principle. Based on this principle, we derive an equation to model the initial ballistic phase of movement in order to predict movement distance and direction. We demonstrate through experimentation that we can successfully model pointing motion to identify a region of likely targets on the computer display. Next, we characterize the effects of target size and target distance on prediction accuracy. We demonstrate that there exists a linear relationship between prediction accuracy and target distance and that this relationship can be leveraged to create a probabilistic model for each target on the computer display. We then demonstrate how these probabilities could be used to enable pointing facilitation in modern computer interfaces.

Finally, we demonstrate that the results from our evaluation of our technique are supported by the current motor control literature. In addition, we show that our technique provides optimal accuracy for any optimal accuracy when prediction of motion endpoint is performed using only the ballistic components of motion and before 90% of motion distance.