Patrick Petersen
Research Scientist
Werdegang
Patrick Petersen has studied Computer Science at the Karlsruhe Institute of Technology (KIT). During his study he focused on cognitive systems and parallel computing. He wrote his master thesis entitled "User interface design, implementation and evaluation for image change detection" at Fraunhofer IOSB. Since November 2017 he has been employed as a Research Scientist at FZI in the department for Embedded Systems and Sensors Engineering with the focus on automotive topics.
Publications
Articles (1)
- Absicherung der Reichweitenschätzung von Elektrofahrzeugen basierend auf aufgezeichneten RealdatenInfoDetails
Patrick Petersen, Stefan Otten, Adam Thor Thorgeirsson, Stefan Scheubner, 2019
Der Energieverbrauch eines Elektrofahrzeugs hängt stark von fahrer-, fahrzeug-, strecken- und umgebungsbezogenen Faktoren ab. Das FZI Forschungszentrum Informatik zeigt, wie aufgezeichnete Realdaten aus Fahrzeugen zur simulationsbasierten Absicherung sowie zur Entwicklung und Optimierung einer zuverlässigen und genauen Reichweitenprädiktion beitragen.
Conference Proceedings (2)
- Validation of range estimation for electric vehicles based on recorded real-world driving dataInfoDetails
Patrick Petersen, Stefan Scheubner, Jacob Langner, Stefan Otten, Moritz Vaillant, Sebastian Fünfgeld and Eric Sax, 2019
Electrification of vehicles is a growing trend in the automotive industry. Battery electric vehicles offer the potential to reduce greenhouse gas emissions, but short maximum range and missing charging infrastructure limits user acceptance. Range anxiety is a great challenge for battery electric vehicle drivers, therefore accurate methods for range estimation are required to satisfy customer needs. Novel algorithms for range estimation include many information sources such as traffic, geographical and weather data. The increase of algorithmic complexity and the behavior of various non-deterministic influences lead to a high demand for intensive verification and validation methods for such predictive features. In this paper, we propose a methodology for the verification and validation of range estimation algorithms based on recorded real-world driving data. The steadily growing pool of recorded test drives from test campaigns enables statistically significant testing. A generalization step enables the usage of all recorded data regardless of the vehicles architecture. New software versions of range estimation algorithms can be tested and a higher feature maturity can be achieved without the need for cost- and time-intensive real-world test drives. This approach is demonstrated and evaluated in a small test campaign.
- Training and Validation Methodology for Range Estimation AlgorithmsInfoDetails
Patrick Petersen, Adam Thorgeirsson, Stefan Scheubner, Stefan Otten, Frank Gauterin, Eric Sax, 2019
Estimating the range of battery electric vehicles is one of the most challenging topics for the current trend in the automotive industry, the electrification of vehicles. Range anxiety still limits the adoption of battery electric vehicles. Since the range estimation is dependent on different influencing factors, complex algorithms to accurately estimate the vehicles consumption are required. To evaluate the accuracy of data-driven machine learning algorithms, an exhaustive training and validation procedure is mandatory. In this paper, we propose a novel methodology for the development and validation of range estimation algorithms based on machine learning validation approaches. The proposed methodology considers the evaluation of driver-specific and driver-unspecific performance. In addition, an error measure is introduced to assess the performance of range estimation algorithms. This approach is demonstrated and evaluated on a set of recorded real-world driving data. It is shown that our approach helps to analyze the performance of the range estimation algorithm and the influences of different parameter sets.
Export search result as .bib
Kontakt
Telefon: +49 721 9654-187
E-Mail: petersen@ fzi.de- Absicherung der Reichweitenschätzung von Elektrofahrzeugen basierend auf aufgezeichneten RealdatenInfoDetails