Predicting Drivers’ Takeover Readiness and Designing an Adaptive In-Vehicle Alert System

Status: In Progress

Lead Researcher(s)

Xi Jessie Yang
Assistant Professor of Industrial and Operations Engineering, College of Engineering and Assistant Professor of Information, School of Information

Project Team

Anuj Pradhan
Former Assistant Research Scientist, University of Michigan Transportation Research Institute

Lionel Robert
Former Assistant Research Scientist, University of Michigan Transportation Research Institute

Dawn Tilbury
Former Assistant Research Scientist, University of Michigan Transportation Research Institute

Project Abstract

In this project, we aim to predict drivers’ takeover readiness and design an adaptive alert system. The proposed research activity will be coordinated under three tasks: (1) Investigate drivers’ takeover performance in highly automated driving by conducting a human subject experiment, leveraging driving simulators at the U-M Transportation Research Institute. Participants’ physiological data and data from the driving scenario will be collected and serve as the input to the computational model. (2) Computationally predict drivers’ takeover readiness in real time by developing a deep-learning model formulated on the convolutional neural networks architecture. (3) Design and evaluate an adaptive in-vehicle alert system. Based on the results from tasks 1 and 2, we will design a multimodal alert system based on the framework of multiple resource theory that will act adaptively in response to drivers’ takeover readiness. We will conduct a human-subject experiment to evaluate the effectiveness of the adaptive in-vehicle alert system.

Project Outcome

Algorithms to detect drivers’ takeover readiness and an adaptive in-vehicle alert system.


BUDGET YEAR: 2018-01-01
IMPACT: SAFETY
RESEARCH CATEGORY: HUMAN FACTORS