Mindlessly Driving or Singing Along: Measuring Driving Performance in ACT-R

Minculescu, Andreea (2022) Mindlessly Driving or Singing Along: Measuring Driving Performance in ACT-R. Bachelor's Thesis, Artificial Intelligence.

Preview	Text bAI_2022_MinculescuA.pdf Download (1MB) | Preview
	Text toestemming.pdf Restricted to Registered users only Download (115kB)

Abstract

Driving is a complex and highly demanding task. Since multitasking typically leads to decreased performance of the main task, it is expected that any concurrent task would interfere with driving performance. Instead, a human study showed that paying full attention to the road while in a monotonous environment results in marginally worse driving performance than if one were driving and listening to the radio at the same time. One possible explanation is that a monotonous driving environment stimulates mind-wandering, which may be more demanding, from a cognitive standpoint, than a simple-enough secondary task. The present study tries to verify this hypothesis by augmenting an ACT-R model of human driving behaviour with i) mind-wandering behaviour and ii) a secondary task of listening to the radio. Results show that the listening model performed significantly better than the mind-wandering model, thus validating the findings of the human study. Overall, this study demonstrated how computational models can be used to provide insights into common misconceptions regarding in-vehicle device design and, more generally, driver safety.

Item Type:	Thesis (Bachelor's Thesis)
Supervisor name:	Borst, J.P.
Degree programme:	Artificial Intelligence
Thesis type:	Bachelor's Thesis
Language:	English
Date Deposited:	14 Jul 2022 09:18
Last Modified:	14 Jul 2022 09:18
URI:	https://fse.studenttheses.ub.rug.nl/id/eprint/27844

Actions (login required)

View Item