Using Ontology-Based Traffic Models for More Efficient Decision Making of Autonomous Vehicles

The paper describes how a high-level abstract world model can be used to support the decision-making process of an autonomous driving system. The approach uses a hierarchical world model and distinguishes between a low-level model for the trajectory planning and a high-level model for solving the traffic coordination problem. The abstract world model used in the CyberCars-2 project is presented. It is based on a topological lane segmentation and introduces relations to represent the semantic context of the traffic scenario. This makes it much easier to realize a consistent and complete driving control system, and to analyze, evaluate and simulate such a system.