Novel Approaches to Cognitive Load Estimation in Automated Driving Systems
Author ORCID Identifier
https://orcid.org/0000-0001-8875-3784 : Prarthana Pillai
Standing
Graduate (Masters)
Type of Proposal
Oral Research Presentation
Faculty Sponsor
Balasingam, Balakumar Dr.; Biondi, Francesco Dr.;
Proposal
System automation with humans in the loop is one of the biggest challenges in the 21st century. With technological elements embedded in all aspects of our everyday life, it is essential to measure the level of cognitive load experienced by humans, in order to ensure safety during the operation of automated systems. For instance, in driving environments, inaccurate estimation of cognitive load may result in greater crash risk due to driver distraction and as a result, accurate and effective driver monitoring systems through non-invasive means must be developed for safe adoption in Automated Driving Systems. The proposed work involves analyzing physiological data, such as eye-tracking data, response time to Detection Response Task, and heart rate, collected from participants at the Human Systems Lab (HSLab) while they performed tasks of varying difficulty in a simulated driving environment. Objective-1: This research’s first objective is to examine eye-gaze metrics such as Entropy, Nearest Neighbor Index, Eyes-Off-Road Time, Glance-based statistics from eye-gaze data using MATLAB and R Studio. Also, signal processing approaches to improve the aforementioned eye-gaze metrics will be investigated. Objective-2: It is reported in literature that heart rate has a positive correlation with cognitive load. The second objective will confirm this using the analysis of ECG data collected at HSLab. Objective-3: The final objective is to examine multi-modal physiological data on a temporal domain to accurately estimate the cognitive load of drivers. This research will contribute to the development of novel and more reliable cognitive load measures for the automotive industry.
Availability
March 31, April 1 (12-3pm)
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Novel Approaches to Cognitive Load Estimation in Automated Driving Systems
System automation with humans in the loop is one of the biggest challenges in the 21st century. With technological elements embedded in all aspects of our everyday life, it is essential to measure the level of cognitive load experienced by humans, in order to ensure safety during the operation of automated systems. For instance, in driving environments, inaccurate estimation of cognitive load may result in greater crash risk due to driver distraction and as a result, accurate and effective driver monitoring systems through non-invasive means must be developed for safe adoption in Automated Driving Systems. The proposed work involves analyzing physiological data, such as eye-tracking data, response time to Detection Response Task, and heart rate, collected from participants at the Human Systems Lab (HSLab) while they performed tasks of varying difficulty in a simulated driving environment. Objective-1: This research’s first objective is to examine eye-gaze metrics such as Entropy, Nearest Neighbor Index, Eyes-Off-Road Time, Glance-based statistics from eye-gaze data using MATLAB and R Studio. Also, signal processing approaches to improve the aforementioned eye-gaze metrics will be investigated. Objective-2: It is reported in literature that heart rate has a positive correlation with cognitive load. The second objective will confirm this using the analysis of ECG data collected at HSLab. Objective-3: The final objective is to examine multi-modal physiological data on a temporal domain to accurately estimate the cognitive load of drivers. This research will contribute to the development of novel and more reliable cognitive load measures for the automotive industry.