Differentiating Cognitive Load Using a Modified Version of AttenD

Abstract

Voice interfaces offer promise in allowing drivers to keep their eyes on-road and hands on-wheel. In relieving visualmanual demand, there is the potential for voice-enabled interfaces to inadvertently shift the burden of load to cognitive resources. Measurement approaches are needed that can identify when and to what extent cognitive load is present during driving. A modified form of the AttenD algorithm was applied to assess the amount of cognitive load present in a set of auditory-vocal task interactions. These tasks were subset from a larger on-road study conducted in the Boston area of driver response during use of an in-vehicle voice system [22]. The modified algorithm differentiated among the set of auditory-vocal tasks examined-and may be useful to HMI practitioners who are working to develop and evaluate HMIs to support drivers in managing their attention to the road, and in the development of real-time driver attention monitoring systems.

Assessment of Secondary Tasks Based on Drivers’ Eye-Movement Features

“…Many studies have evaluated the visual impact of secondary tasks based on the AttenD algorithm. Seppelt et al [15][16][17] used the AttenD algorithm to compare the visual characteristics of distracted driving between near-crash and crash data collected in the 100-Car Naturalistic Driving Study (NDS). Mehler et al [18] considers the strategic nature of how glances are distributed both off and on-road over the course of an HMI interaction, and proposed an attention buffer metric to evaluate distracted driving.…”