Jacob Langner
Wissenschaftlicher Mitarbeiter
Werdegang
Jacob Langner hat an der Universität Rostock Wirtschaftsinformatik studiert. Während des Studiums legte er seinen persönlichen Schwerpunkt zunehmend auf Datenbank- und Informationssysteme. In seiner Masterarbeit befasste er sich mit der "Entwicklung und Bewertung von Verfahren zur inkrementellen Schema-Extraktion aus NoSQL-Datenbanken". Im November 2016 hat er als wissenschaftlicher Mitarbeiter im Forschungsbereich ESS seine Tätigkeit am FZI begonnen. In seiner Forschung beschäftigt er sich mit der datengetriebenen Entwicklungsunterstützung von hochautoamtisierenden Fahrfunktionen - insbesondere mit der Bewertung und Applikation solcher Systeme. Seit Januar 2019 ist er stellvertretender Abteilungsleiter für den Schwerpunkt Automotive Systems Engineering.
Publikationen
Konferenzbeitrag (8)
- Qualitative Feature Assessment for Longitudinal and Lateral Control-FeaturesDetails
Jacob Langner, Christian Seiffer, Stefan Otten, Kai-Lukas Bauer, Marc Holzäpfel, Eric Sax, 2020
- A Process Reference Model for Virtual Application of Predictive Control FeaturesDetails
Jacob Langner, Kai-Lukas Bauer, Marc Holzäpfel, Eric Sax , 2020
- Logical Scenario Derivation by Clustering Dynamic-Length-Segments Extracted from Real-World-Driving-DataInfoDetails
Jacob Langner, Hannes Grolig, Stefan Otten, Marc Holzäpfel and Eric Sax, 2019
For the development of Advanced Driver Assistant Systems (ADAS) and Automated Driving Systems (ADS) a change from test case-based testing towards scenario-based testing can be observed. Based on current approaches to define scenarios and their inherent problems, we identify the need to extract scenarios including the static environment from recorded real-world-driving-data. We present an approach, that solves the problem to extract dynamic-length-segments containing a single scenario. These segments are enriched with a feature vector with information relevant for the feature under test. By clustering these scenarios a logical scenario catalog is created, containing all scenarios within the test data. Corner cases are represented as well as common scenarios. An accumulated total length can be calculated for each logical scenario, giving a brief understanding about existing test coverage of the scenario.
- Validation of range estimation for electric vehicles based on recorded real-world driving dataDetails
Petersen, Patrick and Langner, Jacob and Otten, Stefan and Sax, Eric and Scheubner, Stefan and Vaillant, Moritz and Fünfgeld, Sebastian, 2019
- Estimating the Uniqueness of Test Scenarios derived from Recorded Real-World-Driving-Data using AutoencodersInfoDetails
Jacob Langner, Johannes Bach, Lennart Ries, Stefan Otten, Marc Holzäpfel and Eric Sax, 2018
Advanced Driver Assistant Systems (ADAS) use a multitude of input signals for tasks like trajectory planning and control of vehicle dynamics provided by a large variety of information sources such as sensors and digital maps. To assure the feature?s valid behavior all realistically possible environmental situations have to be tested. The test scenarios used for simulation can be derived from real-world-driving-data. However, the significance of derived scenarios is weakened by repetitive similar situations within the driving data, which increase the test efforts without providing new insights regarding the test of the ADAS. In this contribution, an automated selection algorithm for test scenarios based on relevant environmental parameters is presented. Starting with a randomly selected initial testset, the machine-learning concept of autoencoders is utilized to recognize novel scenarios within the data pool, which are iteratively added to the initial testset. Furthermore, the key parameters for the autoencoder?s performance are shown in depths. The approach is fully automated, so that the identified novel scenarios within an entire testset are automatically combined to a reduced testset of unique relevant scenarios. The achieved testset reduction and thereby the saving potential in simulation time is demonstrated on a dataset including several thousand test kilometers.
- Test Scenario Selection for System-Level Verification and Validation of Geolocation-Dependent Automotive Control SystemsInfoDetails
Johannes Bach, Jacob Langner, Stefan Otten, Marc Holzäpfel and Eric Sax, 2017
Enhanced capabilities of sensors and digital maps for intelligent vehicles lead to a complex and multivariant system environment with a broad variety of situations and traffic scenarios. To assure the feature under development's valid behavior, the sample of scenarios evaluated for Verification & Validation (VV) needs to proof substantial coverage of all possible situations. Currently applied (VV) activities on system-level are in a large part based on real world tests. These are not scalable to sufficiently cover the variant system environment. Our previously introduced Reactive-Replay enables substantial coverage by reuse of recorded real world data in closed-loop simulation. In this contribution we present an approach to determine the relevance of recorded scenarios and derive efficient sets of test scenarios. Our two-step approach starts with a specification-based classification-tree for initial scenario selection. A data-driven reduction of the initial scenario set is achieved by the following analysis of covered parameter spaces. The final consolidated test set avoids repetitive situations while ensuring a significant diversity of the sampled system environment.
- Framework for using real driving data in automotive feature development and validationInfoDetails
Jacob Langner, Johannes Bach, Stefan Otten, Carl Esselborn, Marc Holzäpfel, Michael Eckert and Eric Sax, 2017
The increasing complexity and interconnectivity of automotive features raises the significance of comprehensive verification and validation activities. High-level automotive features use the information provided by complex environmental perception sensors and systems. Due to the rising number of these sensors and the usage of enhanced digital maps, System level verification and validation for high-level features has become a challenge, that is often tackled by a combination of real world tests and simulation approaches. In this contribution we present a method, that combines the realism of real world tests with the scalability of simulation approaches. In the presented framework a feature under development is executed in a Software-in-the-Loop environment with the help of recorded real world driving data. With the steadily growing pool of recorded test drives from test campaigns and country approvals, large scale simulations have been facilitated. This enables statistically significant assertions, continuous maturity tracking as well as geolocation-dependent evaluation of the feature under test. The framework makes these large scale simulations feasible during automotive feature development by utilizing parallelization concepts to achieve simulation speeds of thousands of kilometers within minutes and by reducing adaptation overhead for changes in the feature's software code to a minimum.
- Data-Driven Development, A Complementing Approach for Automotive Systems EngineeringInfoDetails
Johannes Bach, Jacob Langner, Stefan Otten, Marc Holzäpfel and Eric Sax, 2017
Established methods and processes in the field of Automotive Systems Engineering (ASE) are challenged by the rising complexity of current features. Expanding system boundaries, tighter interconnections of functional elements, increasingly complex algorithms and an ever growing operational domain generate a multitude of different scenarios that require consideration during specification, design, implementation and testing. This paper reflects the current practice on the example of the Automotive SPICE process reference for system and software development in the automotive domain. It then contemplates on opportunities of consistent usage of recorded vehicle data throughout all phases of automotive development. Our concept of data-driven development is not intended to replace the current practice but to complement it. A summary of our previous work demonstrates the practicability of the concept on the basis of the development of a Predictive Cruise Control (PCC) feature. The contribution concludes with a scalable concept for the large scale application of data-driven development in ASE.
Export Suchergebnis .bib
Kontakt
Telefon: +49 721 9654-154
E-Mail: langner@ fzi.de- Qualitative Feature Assessment for Longitudinal and Lateral Control-FeaturesDetails