Du, Na
(2022)
Modeling Driver Situational Awareness in Highly Automated Driving.
In: Pitt Momentum Fund 2022.
Abstract
Situational awareness is important to drivers in automated driving. Maintaining situational awareness of driving environments can help drivers avoid unnecessary interventions with automated driving systems and negotiate challenging scenarios where human takeovers are needed. However, little research has attempted to monitor and predict driver situational awareness in real time. The proposed project aims to fill the research gaps with two specific objectives. First, the project will systematically investigate driver situational awareness in a variety of non-driving-related-task, vehicle, and environmental conditions. Second, the project will develop machine learning models to predict driver situational awareness using their neurophysiological signals (e.g., gaze behaviors and heart rate activities) and environment data. We will conduct a human-subject experiment in a driving simulator to capture participants’ self-report of situational awareness and neurophysiological signals. The findings will provide empirical answers to policy makers and car manufacturers regarding the development of in-vehicle monitoring and alert systems to ensure driving safety. The de-identified dataset and source code of machine learning models can be expanded and improved upon by the project team and serve as pilot data to apply for external grants such as NSF and DARPA.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
Metrics
Monthly Views for the past 3 years
Plum Analytics
Altmetric.com
Actions (login required)
 |
View Item |
![[feed]](/images/feed-icon-32x32.png){kind=icon}