header

Driving Assistant Using ChatGPT Pre-Generated Messages in Simulator-Based Driving Assessment: Toward Low-Cost Driving Assessment for Stroke Patients

43 Pages Posted: 6 Feb 2024 Publication Status: Under Review

See all articles by Gunt Chanmas

Gunt Chanmas

Ritsumeikan University

Pittawat Taveekitworachai

Ritsumeikan University

Xiao You

Ritsumeikan University

Ruck Thawonmas

Ritsumeikan University

Chakarida Nukoolkit

King Mongkut’s University of Technology (KMUTT)

Piyapat Dajpratham

Mahidol University

Abstract

This paper presents a novel approach for a low-cost simulator-based driving assessment system incorporating a speech-based assistant, using pre-generated messages from ChatGPT to achieve real-time interaction during the assessment. Stroke patients often face challenges during rehabilitation to re-acquire their driving skills. One essential process during rehabilitation is driving assessment to determine the fitness-to-drive of the patients. Traditional assessment approaches, like on-road evaluation, though reliable, can be risky, costly, and inaccessible. Simulator-based assessment using stationary driving simulators offers a safer evaluation and can be tailored to specific needs. However, these simulators are often only available to research-focused institutions due to their cost. To address this issue, our study proposes a system with the aforementioned properties aiming to enhance drivers' situational awareness and foster positive emotional states, i.e., high valence and medium arousal, while assessing participants to prevent subpar performers from proceeding to the next stages of assessment and/or rehabilitation. In addition, to provide an initial validation of the effectiveness of our proposed system, we preliminary investigate the effectiveness of our proposed system by engaging 32 healthy university students, evenly distributed into two experimental groups, where driving sessions alternate between utilizing the speech-based assistant and driving without it. The speech-based assistant provides timely guidance adaptable to the ever-changing context of the driving environment and vehicle state. The study's preliminary outcomes reveal encouraging progress, highlighting improved driving performance and positive emotional states when participants are engaged with the assistant during the assessment. Notably, a statistical significance is observed between driving sessions with and without the assistant, underscoring its potential in improving driving performance during simulator-based driving assessment by assisting drivers in effectively navigating challenges while nurturing positive emotional states. The results support our upcoming research phase, which examines the proposed system's effectiveness as the initial step in assessing stroke patients' driving abilities.

Keywords: Driving assessment, Large language model, Vector database, CARLA driving simulator, LLMs-integrated system

Suggested Citation

Chanmas, Gunt and Taveekitworachai, Pittawat and You, Xiao and Thawonmas, Ruck and Nukoolkit, Chakarida and Dajpratham, Piyapat, Driving Assistant Using ChatGPT Pre-Generated Messages in Simulator-Based Driving Assessment: Toward Low-Cost Driving Assessment for Stroke Patients. Available at SSRN: https://ssrn.com/abstract=4711961 or http://dx.doi.org/10.2139/ssrn.4711961

Gunt Chanmas

Ritsumeikan University ( email )

Pittawat Taveekitworachai

Ritsumeikan University ( email )

Xiao You

Ritsumeikan University ( email )

Ruck Thawonmas (Contact Author)

Ritsumeikan University ( email )

Japan

Chakarida Nukoolkit

King Mongkut’s University of Technology (KMUTT) ( email )

Piyapat Dajpratham

Mahidol University ( email )

69 Vipawadee Rangsit Road
Phayatai, Bangkok, 10400
Thailand

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
18
Abstract Views
80
PlumX Metrics