Machine Learning, Human Factors and Security Analysis for the Remote Command of Driving: An Mcity Pilot

Principal Investigator(s):

Robert Hampshire, Associate Professor – Gerald R. Ford School of Public Policy Research
Associate Professor – University of Michigan Transportation Research Institute (UMTRI)
Research Associate Professor – Michigan Institute for Data Science (MIDAS)
Affiliated Faculty Member of Industrial and Operations Engineering – University of Michigan
Principal Deputy Assistant Secretary for Research and Technology – United States Department of Transportation (USDOT)
Shan Bao, Associate Research Scientist – The University of Michigan Transportation Research Institute
Associate Professor of Industrial and Manufacturing Systems Engineering – University of Michigan-Dearborn
Walter Lasecki, Assistant Professor of Computer Science and Engineering – The University of Michigan

Project Abstract:
Both human drivers and autonomous vehicles are now able to drive relatively well in ‘typical’ (frequently- encountered) settings, but fail in exceptional cases. Worse, these exceptional cases often arise suddenly, leaving human drivers with a few seconds at best to react—exactly the setting that people perform worst in. This work proposes methods for leveraging groups of remote operators to provide assistance on-demand. Unlike prior work, we introduce collective workflows that enable groups of operators to significantly outperform any of the constituent individuals on control and correction tasks. We propose to develop a software platform for Mcity that enables a group of remote operators to command the autonomous test vehicles at Mcity. A pilot study will be conducted at the Mcity Test Facility.

Institution(s): University of Michigan Transportation Research Institute
University of Michigan – Ann Arbor

Award Year: 2018

Research Thrust(s): Control & Operations, Enabling Technology, Human Factors

Project Form(s):