Re-engaging Driver Attention using ChatGPT: A Multimodal Study on Stress Impact and Driving Performance

Author

Alaa Zaki Elfiqi, The American University in Cairo AUCFollow

Abstract

Driving is considered a complex task that requires continuous focus and attention from the driver. Driving performance can also be impacted by changes in the driver’s stress level. However, limited research explores methods to address this challenge. With the current advances in Large Language Models (LLMs) and their ability to engage in human-like interaction, this study investigates the potential of using ChatGPT, designed to speak Egyptian Arabic, in re-engaging driver attention under different driving scenarios for low-stress and high-stress conditions within a virtual reality (VR) environment driving simulator. Drivers were asked to follow a leading car into two scenarios with and without ChatGPT while physiological data (Electroencephalography (EEG), eye-tracking, heart rate, galvanic skin response (GSR)) and driving performance parameters (reaction time, distance to lead vehicle, and number of collisions) were recorded during the sessions. The results indicate that open-ended voice conversation ChatGPT can help improve driver performance compared to not using ChatGPT. In the high-stress scenario, the EEG theta band increased significantly, which is associated with cognitive control, while the Perceived Stress Scale reduced by 16.64% in addition to an improvement of 5.78% in the driver’s reaction time. In the low-stress scenario, visual attention was improved as indicated by a decrease in parietal-occipital alpha band, and a significant increase in pupil diameter, and the performance improved by 5.32%. This work contributes to the integration of EEG-VR-ChatGPT, paving the way for adaptive Artificial Intelligence (AI) driver assistance in future research.

TRANSLATE with x English Arabic Hebrew Polish Bulgarian Hindi Portuguese Catalan Hmong Daw Romanian Chinese Simplified Hungarian Russian Chinese Traditional Indonesian Slovak Czech Italian Slovenian Danish Japanese Spanish Dutch Klingon Swedish English Korean Thai Estonian Latvian Turkish Finnish Lithuanian Ukrainian French Malay Urdu German Maltese Vietnamese Greek Norwegian Welsh Haitian Creole Persian TRANSLATE with COPY THE URL BELOW Back EMBED THE SNIPPET BELOW IN YOUR SITE Enable collaborative features and customize widget: Bing Webmaster Portal Back

TRANSLATE with x English Arabic Hebrew Polish Bulgarian Hindi Portuguese Catalan Hmong Daw Romanian Chinese Simplified Hungarian Russian Chinese Traditional Indonesian Slovak Czech Italian Slovenian Danish Japanese Spanish Dutch Klingon Swedish English Korean Thai Estonian Latvian Turkish Finnish Lithuanian Ukrainian French Malay Urdu German Maltese Vietnamese Greek Norwegian Welsh Haitian Creole Persian TRANSLATE with COPY THE URL BELOW Back EMBED THE SNIPPET BELOW IN YOUR SITE Enable collaborative features and customize widget: Bing Webmaster Portal Back

TRANSLATE with x English Arabic Hebrew Polish Bulgarian Hindi Portuguese Catalan Hmong Daw Romanian Chinese Simplified Hungarian Russian Chinese Traditional Indonesian Slovak Czech Italian Slovenian Danish Japanese Spanish Dutch Klingon Swedish English Korean Thai Estonian Latvian Turkish Finnish Lithuanian Ukrainian French Malay Urdu German Maltese Vietnamese Greek Norwegian Welsh Haitian Creole Persian TRANSLATE with COPY THE URL BELOW Back EMBED THE SNIPPET BELOW IN YOUR SITE Enable collaborative features and customize widget: Bing Webmaster Portal Back

TRANSLATE with x English Arabic Hebrew Polish Bulgarian Hindi Portuguese Catalan Hmong Daw Romanian Chinese Simplified Hungarian Russian Chinese Traditional Indonesian Slovak Czech Italian Slovenian Danish Japanese Spanish Dutch Klingon Swedish English Korean Thai Estonian Latvian Turkish Finnish Lithuanian Ukrainian French Malay Urdu German Maltese Vietnamese Greek Norwegian Welsh Haitian Creole Persian TRANSLATE with COPY THE URL BELOW Back EMBED THE SNIPPET BELOW IN YOUR SITE Enable collaborative features and customize widget: Bing Webmaster Portal Back TRANSLATE with x English Arabic Hebrew Polish Bulgarian Hindi Portuguese Catalan Hmong Daw Romanian Chinese Simplified Hungarian Russian Chinese Traditional Indonesian Slovak Czech Italian Slovenian Danish Japanese Spanish Dutch Klingon Swedish English Korean Thai Estonian Latvian Turkish Finnish Lithuanian Ukrainian French Malay Urdu German Maltese Vietnamese Greek Norwegian Welsh Haitian Creole Persian TRANSLATE with COPY THE URL BELOW Back EMBED THE SNIPPET BELOW IN YOUR SITE Enable collaborative features and customize widget: Bing Webmaster Portal Back

School

School of Sciences and Engineering

Department

Robotics, Control & Smart Systems Program

Degree Name

MS in Robotics, Control and Smart Systems

Graduation Date

Summer 8-19-2025

Submission Date

9-16-2025

First Advisor

Khalil ElKhodary

Second Advisor

Seif Eldawlatly

Committee Member 1

Amr El Mougy

Committee Member 2

Mervat Abu-Elkheir

Committee Member 3

Mostafa Youssef

Extent

135 p.

Document Type

Master's Thesis

Institutional Review Board (IRB) Approval

Approval has been obtained for this item

Disclosure of AI Use

Thesis text drafting

Recommended Citation

APA Citation

Elfiqi, A. Z. (2025).Re-engaging Driver Attention using ChatGPT: A Multimodal Study on Stress Impact and Driving Performance [Master's Thesis, the American University in Cairo]. AUC Knowledge Fountain.
https://fount.aucegypt.edu/etds/2598

MLA Citation

Elfiqi, Alaa Zaki. Re-engaging Driver Attention using ChatGPT: A Multimodal Study on Stress Impact and Driving Performance. 2025. American University in Cairo, Master's Thesis. AUC Knowledge Fountain.
https://fount.aucegypt.edu/etds/2598