This paper presents a modular framework for traffic regulations based decision-making of automated vehicles. It builds on a semantic traffic scene representation formulated as ontology and includes knowledge about traffic regulations. The semantic representation supports traffic situation classification by reasoning, providing improved situational awareness for the automated vehicle. Decision-making rules are directly derived from traffic regulations and concepts used in the ontology are harmonized with concepts used in traffic regulations. Due to the modular structure of the developed ontology, switching between different sets of national traffic regulations becomes a simple process. The methodology is evaluated for a variety of traffic scenarios, building up from basic to complex urban scenarios containing intersections, traffic regulating police officers and crossing street railways.

Abstract-The automotive domain is challenged by the increasing importance of Information Technology (IT) based functions. To show the possibilities of modern IT systems, a demonstrator car was developed in RACE (Robust and Reliant Automotive Computing Environment for Future eCars) based on a completely redesigned E/E architecture, which supports the integration of mixed-criticality components and offers features like Plug&Play. This paper presents the architecture and components of this vehicle prototype, which is equipped with modern systems such as Steer-by-Wire without mechanical fallback. It was designed to support future driver assistance systems, e.g. to carry out autonomous parking maneuvers onto an inductive charging station, a task, which is hard to achieve accurately enough for a human driver. Therefore, a special emphasis lies on the description of the sensor set for automated operation.

Although many research vehicle platforms for autonomous driving have been built in the past, hardware design, source code and lessons learned have not been made available for the next generation of demonstrators. This raises the efforts for the research community to contribute results based on real-world evaluations as engineering knowledge of building and maintaining a research vehicle is lost. In this paper, we deliver an analysis of our approach to transferring an open source driving stack to a research vehicle.We put the hardware and software setup in context to other demonstrators and explain the criteria that led to our chosen hardware and software design. Specifically, we discuss the mapping of the Apollo driving stack to the system layout of our research vehicle, fortuna, including communication with the actuators by a controller running on a real-time hardware platform and the integration of the sensor setup. With our collection of the lessons learned, we encourage a faster setup of such systems by other research groups in the future.

No abstract