Lijnzaad, Gilles (2021) Predicting Working Memory Load and Visuospatial Demands During Driving Using Eye-Tracking. Bachelor's Thesis, Artificial Intelligence.
|
Text
bAI_2021_LijnzaadGDF.pdf Download (645kB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (118kB) |
Abstract
In adaptive driving, control over the vehicle is dynamically divided between the driver and an intelligent system. In order to develop a system that adapts its degree of control to the mental state of the driver, a robust method of measuring their cognitive load is required. This study focuses on pupillometry as a possible predictor for cognitive load, which is here defined as a combination of working memory load (WML) and visuospatial demands. Additionally, we were interested in the effect of cognitive load on speed-keeping efforts, as measured by eye fixations on the speedometer. A simulated-driving experiment with eye-tracking was conducted in which WML and visuospatial demands were manipulated separately. In the simulation participants drove on a straight highway for 60 minutes. WML was manipulated by an n-back task (n = 0,1,2,3,4), performed by means of speed regulation. Visuospatial demands were manipulated by a change in the driving environment: a construction site with reduced lane width, increasing driving difficulty. Results indicate that pupil size is a predictor for WML, but not for visuospatial demands. We conclude that in order to fully capture cognitive load while driving, pupillometry should be used in combination with a measure of visuospatial demands. Moreover, a negative correlation between WML and number of fixations on the speedometer was found. This highlights speed-keeping aid as an application for adaptive automation based on cognitive load.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Borst, J.P. and Held, M.L.C. |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 06 Jul 2021 10:25 |
| Last Modified: | 06 Jul 2021 10:25 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/25006 |
Actions (login required)
 |
View Item |