Gábor Orosz: 'Conflict analysis for decision making and control of connected automated vehicles'

Mathematical Challenges and Opportunities for Autonomous Vehicles 2020
Workshop II: Safe Operation of Connected and Autonomous Vehicle Fleets

"Conflict analysis for decision making and control of connected automated vehicles"
Gábor Orosz - University of Michigan, Department of Mechanical Engineering

Abstract: We analyze how wireless vehicle-to-vehicle (V2V) communication can be utilized to prevent conflicts between road participants in mixed traffic scenarios where connected automated vehicles (CAVs) interact with connected human-driven vehicles (CHVs). The key idea is to find boundaries in state space that allow CAVs to make safe decisions far away from the conflict zone. This way CAVs are able to maintain safety while using mild control actions that benefit both the CAVs as well as the surrounding human-dominated traffic. Requirements for the quality of V2V communications are determined to ensure the performance of the decision making and control algorithms. The results are demonstrated experimentally using real automobiles and class-8 trucks.

Institute for Pure and Applied Mathematics, UCLA
October 29, 2020