Ljubo Mercep

The software car: Building ICT architectures for future electric vehicles

Disruptive technologies have the potential to change markets dramatically. The switch from internal combustion engines to electrical engines is such a change. But electric engines for vehicles are only the catalyst for the real change. Most significantly, the architecture and role of information and communication technology (ICT) will change for the vehicle of the future. This paper discusses the results of a study conducted in Germany on the role of ICT architectures. Furthermore, it will present an experimental platform that implements the vision of this study.

Towards the deployment of a centralized ICT architecture in the automotive domain

The effort for the integration of new functionalities in todays vehicles is increasing as the interconnection and verification of the growing amount of heterogeneous and distributed electric control units (ECUs) becomes more difficult. The demand for a new architectural approach that can cope with the increasing complexity and offers possibilities for a smooth integration of future technologies is urgent. Such technologies are drive-by-wire systems or advanced driver assistance systems. This paper extends the previously introduced ICT architecture for future vehicles by the analysis of a possible system, hardware and software architecture and their properties. In addition, a migration path from the current vehicle architecture is suggested and economic impacts of suggested improvements are shown. A short description of differences to AUTOSAR is given. Demonstrators for proof-of-concept and evaluation are also discussed. With this work we have brought the previously described ICT architecture one step closer to the large-scale implementation in the automotive domain.

A case study on implementing future human-machine interfaces

In the scope of the Diesel Reloaded project, we conducted a study on future automotive human-machine interfaces (HMI) with an overview of their relationship to driver assistance systems (DAS). Furthermore, we implemented a series of HMI and DAS concepts in our prototype vehicle and in a modified driving simulator. Emphasis was placed on the following goals: Pushing the complexity away from the driver and inside the intelligent vehicle, developing unified and extendable descriptions of interaction context, defining transitional steps to the long-term goal of user interfaces which augment the driver, leveraging cross-domain technology transfer and addressing relevant societal trends. In this work, we provide a top-level overview of our results and conclusions we drew based upon our two-year research and prototype construction and deployment in the area of human-machine interfaces and driver assistance.

The Innotruck Case Study on A Holistic Approach to Electric Mobility

We present an interdisciplinary approach to electric mobility based on three main research areas: Energy Management, System Architecture and Human–Machine Interface. A flexible energy management model is developed to suit the needs of arbitrary aggregated configurations in different hybrid vehicles. Our modular and data-centric vehicle ICT architecture reduces communication overhead, while addressing component plug-and-play and automotive safety. The classical human–machine interface is extended with a highly integrated HMI module which analyzes the interaction context. A drive-by-wire hybrid vehicle prototype has been constructed, the Innotruck, which serves as both testing ground for the developed concepts and a presentation area for communicating the results to public. Emphasis is placed on the societal importance of our work, impact and dissemination of results. More than 20 industry and research partners contribute directly to the project and the further development of the prototype vehicle.

Reducing the impact of vibration-caused artifacts in a brain-computer interface using gyroscope data

We implemented an artifact prediction method for a saline-pad wireless electroencephalograph equipped with two-axis gyroscope used as a basic brain-computer interface (BCI). The BCI unit serves two purposes in the scope of the project Innotruck. Firstly, it enables remote control of vehicles and other systems over a limited set of trained mental activity. Secondly, it is a source of data for the passive analysis of the operators mental fitness, which is further integrated into the driver assistance systems. The latter aspect has been the focus of our work. Saline-pad electrodes used in consumer grade electronics are prone to errors stemming from vibrations and sudden head movements. The implemented approach successfully preconditions the signal processing pipeline to take such artifacts into account and reduces the later processing overhead.

Human Performance Profiling While Driving a Sidestick-Controlled Car

We have established a metric for measuring human performance while operating a sidestick-controlled car and have used it in conjunction with a known environment type to identify unusual steering trends. We focused on the analysis of the vehicle’s offset from the lane center in the time domain and identified a set of this signal’s features shared by all test drivers. The distribution of these features identifies a specific driving environment type and represents the essence of the proposed metric. We assumed that the driver performance, while operating a sidestick-controlled car, is determined by the environment type on one side and the driver’s own mental state on the other. The goal is to detect the mismatch of the assumed driving environment, gained from the introduced metric, and a ground truth about the actual environmental type, which can be obtained through map and GPS data, in order to identify unusual steering trend possibly caused by a change in driver fitness.