DeepScenario: City Scale Scenario Generation for Automated Driving System Testing & Evaluation

DeepScenario: City Scale Scenario Generation for Automated Driving System Testing & Evaluation

Headshot of CCAT Director, Henry Liu - link directs to their research page
Henry Liu
Shan Bao Headshot - link directs to their research page
Shan Bao
Brian Lin Headshot - link directs to their research page
Brian Lin
UMTRI Logo - link directs to U-M research page

Principal Investigator(s):

Henry Liu, Director – Center for Connected and Automated Transportation (CCAT)
Professor of Civil and Environmental Engineering – The University of Michigan
Research Professor – The University of Michigan Transportation Research Institute
Shan Bao, Associate Research Scientist – The University of Michigan Transportation Research Institute
Associate Professor of Industrial and Manufacturing Systems Engineering – University of Michigan-Dearborn
Brian Lin, Assistant Research Scientist – The University of Michigan Transportation Research Institute

Project Abstract:
In this project, we will build a city-scale scenario generation and simulation platform for ADS testing and evaluation. Under different routes and environmental conditions, the simulation platform can generate testing scenarios dynamically along the route to interact with the CAV and systematically evaluate its performance. Meanwhile, a set of corner cases regarding vulnerable road users (VRUs) will be identified and added to the generated scenario library. We will leverage and extend our existing work in scenario generation and integrate it with VISSIM, CARLA, and Autoware. The platform will also be integrated with the augmented reality testing environment to enable the testing of real CAVs.

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

Project Form(s):
Project Information Form