English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The use of ACT-R to develop an attention model for simple driving tasks Kerstin Sophie Haring (ksharing@fennel.rcast.u-tokyo.ac.jp) Katsumi Watanabe (kw@fennel.rcast.u-tokyo.ac.jp) Research Center for Advanced Science and Technology, The University of Tokyo 4-6-1, Komaba, Meguro-ku, Tokyo, 153-8904, Japan Marco Ragni (ragni@cognition.uni-freiburg.de) Lars Konieczny (lars@cognition.uni-freiburg.de) Center for Cognitive Science, University of Freiburg Friedrichstr. 50, 79098 Freiburg, Germany of these highly complex tasks. Vice versa, it also can provide an indication for the future development of a cognitive architecture by showing what cannot be realized yet. Abstract Driving a car is obviously a complex task and the construction of an ACT-R model of human attention while performing this task is similarly complex along multiple dimensions and presents a challenge to architecture and modeler. This work is a first attempt to develop an integrated driver model of attention in the cognitive architecture ACT-R. The model is able to keep a traffic lane, identifies traffic signs and crossroads in a sparse, simulated environment. Keywords: Driver behavior model; cognitive architecture; ACT-R; Attention Introduction Fig. 2: Screenshot of the environment interaction with ACT-R. The red circle indicates the current visual focus of attention of the model. For most of us, driving a car is one of our everyday tasks. But even for experienced drivers, just the task itself it is a cognitive challenging task involving a big range of human senses like sight, hearing, touch and acceleration. And this is not yet considering secondary tasks like talking on the phone or visual distractions like city illuminations. Luckily, most driving task are not as challenging as the Traffic Light Tree in Fig. 1, an artificial scenario by the French sculptor Pierre Vivant. The simulation environment for this model was restricted to the components the cognitive architecture can recognize. Nevertheless, basic driving scenarios simulating human visual attention and driver behavior could be implemented. The screenshot form the driving environment, which was separately implemented in Lisp for this work, shows from top-down another (blue) vehicle, the focus of attention (red circle) and the navigation point (N) to keep the vehicle in the center of the road. This model focuses on basic reference points like the horizon, a leading car, the border and the center line of the road, crossroads and traffic signs. For example, the model of a driver in the screenshot in Fig. 2 sets the focus of visual attention on the outer border of the road which enables it to reevaluate the center for the N point. In the next step, it will shift the focus of attention to the front and (hopefully) detect the car in front. If so, possible next steps could be the comparison of the distance to a (here fixed) safety distance or an overtaking procedure. The here presented cognitive model should simulates through ACT-R human attention while driving in a simplified environment and produces the behavior for scenarios with other cars, crossroads and traffic signs. Fig. 1: The (thankfully not on a crossroad) installed traffic light sculpture by Pierre Vivant. The cognitive architecture Current attempts to model human attention while driving a car are realized in a quite more simple environment, yet they are quite an important first step towards the modeling The ACT-R (Anderson, 1993; Anderson 2007) cognitive architecture proposes artificial, computational processes that aim to act like a human cognitive system. Most of its basic

The Use of ACT-R to Develop an Attention Model for Simple Driving Tasks