Abstract
A major focus of research into visually guided action (VGA) is the identification of control strategies that map optical information to actions. The traditional approach to this research has been to test the behavioral predictions of a few hypothesized strategies against subject behavior in environments in which various manipulations of available information have been made. While important and compelling results have been achieved with these methods, they are potentially limited by small sets of hypotheses and the methods used to test them. In this study, we introduce a novel application of powerful data-mining and machine-learning techniques in an "assumption-lite" analysis of experimental data that is able to both describe and model human behavior. This method permits the rapid testing of a wide range of possible control strategies using arbitrarily complex combinations of optical variables. Through the use of decision-tree techniques, subject data can be transformed into an easily interpretable, algorithmic form. This output can then be immediately incorporated into a working model of subject behavior. We tested the effectiveness of this method in identifying the optical information and control strategies used by human subjects in a collision-avoidance task. Our analytical results comport with existing research into collision-avoidance control strategies while also providing additional insight not possible with traditional methods. Further, the modeling component of our method produces behavior that closely resembles that of the subjects upon whose data the models were based. Taken together, the findings demonstrate that data-mining and machine-learning techniques provide powerful new tools for analyzing human data and building models that can be applied to a wide range of perception-action tasks.
Meeting abstract presented at VSS 2012