The emerging level 3 autonomous vehicle (L3AV) can perform all aspects of the driving task and allow for complete disengagement of drivers (e.g., sit back and relax) under certain driving scenarios including immediate response (e.g., emergency braking). However, this still requires the driver to be prepared for takeover within a few seconds of warning. Being able to measure and predict the takeover performance (TOP) ahead of time and issue adequate warnings is critical to ensure driver comfort, trust, and safety in the system and acceptance of the technology.

A necessary undertaking in this process is to develop a robust approach to understand the drivers’ capabilities to take over the vehicle safely and promptly in L3 AV under different driving and disengagement scenarios. In this project, we propose an integrated treatment of the drivers’ TOP measured through multimodal physiological features and driving environment data in L3 AVs. We will present the results of data collected from 20 drivers. The drivers were presented with different secondary tasks and driving scenarios in a simulator and their physiological responses were collected using different sensing devices such as electroencephalogram (EEG), galvanic skin response (GSR), and heart rate (HR). The presentation will highlight the relationship between the driver's physiological state such as level of engagement with the secondary task and their TOP.

More about this research: https://myumi.ch/Axbod