Real-Time Decision Making for Autonomous City Vehicles

Abstract

This paper addresses the topic of real-time decision making for autonomous city vehicles, i.e. their ability to make appropriate driving decisions in any city traffic situation. After explaining the research question and addressing the state of research, the paper presents the vehicle decision making & control system architecture, explains the subcomponents which are relevant for decision making (World Model and Driving Maneuver subsystem), and presents the decision making process, which consists of two consecutive stages. While the first decision making stage uses a Petri net to model the safety-critical selection of feasible driving maneuvers, the second stage uses Multiple Criteria Decision Making (MCDM) methods to select the most appropriate driving maneuver, focusing on fulfilling objectives related to efficiency and comfort. Experimental tests in both a 3D simulation and realworld experiments attest that the developed approach is suitable to deal with the complexity of real-world city traffic situations.