Development of Situational Awareness Enhancing Systems for AV-Manual Handover and Other Tasks

Development of Situational Awareness Enhancing Systems for AV-Manual Handover and Other Tasks

Headshot of Samuel Labi. The link directs to their bio page.
Samuel Labi
Headshot of Sikai Chen. The link directs to their bio page.
Sikai Chen
Purdue University Logo. The link directs to the funded research led by this institution.

Principal Investigator(s):

Samuel Labi, Professor of Civil Engineering – Purdue University
Director – NEXTRANS
Sikai Chen, Post-Doctoral Researcher – Center for Connected and Automated Transportation
Post-Doctoral Researcher – NEXTRANS Center at Purdue University
Visiting Research Fellow – Robotics Institute at the School of Computer Science at Carnegie Mellon University 

Project Abstract:
Partially and conditionally automated vehicle systems (AVS) can assist drivers with their driving tasks and have the potential to significantly reduce driving-related burden. Drivers still play a critical role such as monitoring the driving environment when the AVS is engaged and performing certain driving tasks when called upon by the system. However, there is ample evidence in the literature and real-world that drivers cannot maintain necessary situational awareness to safely take over the vehicle when needed due to task underload, vigilance decrement, or over-trust in AVS capabilities. There is a critical need to design mechanisms that assist drivers in maintaining a certain level of situational awareness for promoting a smooth and safe transition to full vehicle automation in the future. This study aims to design an in-vehicle situational awareness – 2 – enhancing system (SAES) to facilitate AV-manual take-over in partially and conditionally automated vehicles. In the first phase, we will develop a periodic visual prompts-based SAES for directing drivers’ attention to selected areas of interest and evaluate its impacts on drivers’ situational awareness and takeover performance. In the second phase, we will develop SAES that generates dynamic visual prompts based on drivers’ level of situational awareness, and dynamic road and traffic conditions. This study will conduct interactive driving simulator-based experiments with SAES to collect driver physiological data (e.g., eye gaze patterns, heart rate, and brain electrical activity) and micro-level driving performance (e.g., steering wheel angle and acceleration/deceleration). The collected data will be used to model the impacts of SAES on drivers’ situational awareness and takeover performance in partial and conditional automation driving environments.

Institution(s): Purdue University

Award Year: 2021

Research Thrust(s): Enabling TechnologyHuman Factors, Modeling & Implementation

Project Form(s):