Modeling Naturalistic Driving Environment with High-Resolution Trajectory Data

Modeling Naturalistic Driving Environment with High-Resolution Trajectory Data

Shuo Feng
Headshot of CCAT Director, Henry Liu - link directs to their research page
Henry Liu
University of Michigan Transportation Research Institute Logo - link directs to U-M research page

Principal Investigator(s):

Shuo Feng, Assistant Research Scientist – The University of Michigan Transportation Research Institute
Henry Liu, Director – Center for Connected and Automated Transportation (CCAT)
Director – Mcity
Professor of Civil and Environmental Engineering – The University of Michigan
Research Professor – The University of Michigan Transportation Research Institute

Project Abstract:
In this project, we will develop a methodological framework for modeling the high-fidelity naturalistic driving environment (NDE) with high-resolution trajectory data. Different from traditional NDE models that mainly match the moments of macroscopic traffic behaviors, the high-fidelity NDE models will match the distributions of microscopic driving behaviors, which are critical for safety-critical applications such as autonomous vehicle testing and training. The large-scale high-resolution data that is being collected by roadside sensors will be leveraged. The developed NDE models will be implemented in the SAFE-TEST toolbox for the safety assessment of autonomous vehicles at the American Center for Mobility, which will significantly expand the toolbox into the complex urban driving environment. Both the high-resolution data collection system and SAFE-TEST toolbox were developed by the PI research team with previous CCAT and Mcity sponsored projects.

Institution(s): University of Michigan Transportation Research Institute

Award Year: 2022

Research Thrust(s): Control & Operations, Enabling Technology, Infrastructure Design & Management, Modeling & Implementation

Project Form(s):
Project Information Form