Towards a Model for Predicting Intention in 3D Moving-Target Selection Tasks

Juan Sebastian Casallas (1, 2) , James H. Oliver (1) , Jonathan W. Kelly (1) , Frédéric Merienne (2) , Samir Garbaya (2)

1 ISU - Iowa State University
2 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]

Novel interaction techniques have been developed to address the difficulties of selecting moving targets. However, similar to their static-target counterparts, these techniques may suffer from clutter and overlap, which can be addressed by predicting intended targets. Unfortunately, current predictive techniques are tailored towards static-target selection. Thus, a novel approach for predicting user intention in moving-target selection tasks using decision-trees constructed with the initial physical states of both the user and the targets is proposed. This approach is verified in a virtual reality application in which users must choose, and select between different moving targets. With two targets, this model is able to predict user choice with approximately 71% accuracy, which is significantly better than both chance and a frequentist approach.

Mots clés: User intention; Prediction; Fitts’ Law; Moving-target selection; Perceived difficulty; Decision trees; Virtual reality

Domaines: Interface homme-machine [cs.HC]; Synthèse d'image et réalité virtuelle [cs.GR]

Juan Sebastian Casallas, James H. Oliver, Jonathan W. Kelly, Frédéric Merienne, Samir Garbaya. Towards a Model for Predicting Intention in 3D Moving-Target Selection Tasks. 10th International Conference, EPCE 2013, Held as Part of HCI International 2013, Jul 2013, Las Vegas, Nevada, Afghanistan. pp.13-22, ⟨10.1007/978-3-642-39360-0_2⟩. ⟨hal-01111100⟩