Wir verwenden Cookies

Wir nutzen Cookies auf unserer Website. Einige von ihnen sind essenziell, während andere uns helfen, diese Website und Ihre Erfahrung zu verbessern.

Essenziell
 
Digital

Wissenschaftliche Publikation

Measurement and Prediction of Situation Awareness in Human-Robot Interaction based on a Framework of Probabilistic Attention

Publikation aus Digital

Dini, A., Murko, C., Paletta, L., Yahyanejad, S., Augsdürfer, U., and Hofbaur, M.

Proc. IEEE/RSJ International Conference on Intelligent Robots and Sys-tems, IROS 2017, Vancouver, Canada, 24-28 September, 2017 , 1/2017

Abstract:

Human attention processes play a major role in the optimization of human-robot interaction (HRI) systems. This work describes a novel methodology to measure and predict situation awareness and from this overall performance from gaze features in real-time. The awareness about scene objects of interest is described by 3D gaze analysis using data from wearable eye tracking glasses and a precise optical tracking system. A probabilistic framework of uncertainty considers coping with measurement errors in eye and position estimation. Comprehensive experiments on HRI were conducted with typical tasks including handover in a lab based prototypical manufacturing environment. The methodology is proven to predict standard measures of situation awareness (SAGAT, SART) as well as performance in the HRI task in real-time and will open new opportunities for human factors based performance optimization in HRI applications.