T. Stefani, J. M. Christensen, A. A. Girija, S. Gupta, U. Durak, F. Köster, T. Krüger, und S. Hallerbach, "Automated Scenario Generation from Operational Design Domain Model for Testing AI-Based Systems in Aviation" CEAS Aeronautical Journal.
@article{dlr207924, publisher = {Springer},
year = {2024},
title = {Automated Scenario Generation from Operational Design Domain Model for Testing AI-Based Systems in Aviation},
journal = {CEAS Aeronautical Journal},
note = {pages = 14},
author = {Stefani, Thomas and Christensen, Johann Maximilian and Girija, Akshay Anilkumar and Gupta, Siddhartha and Durak, Umut and K{\"o}ster, Frank and Kr{\"u}ger, Thomas and Hallerbach, Sven},
abstract = {Applications based on artificial intelligence (AI) promise benefits, ranging from improved performance to increased capabilities in many industries. In the aviation domain, one example is the new Airborne Collision Avoidance System (ACAS X). The current investigation aims at combining ACAS X and AI to maintain its performance while decreasing the memory footprint. However, the anticipation of AI being increasingly used confronts regulators with challenges in terms of safety assurance and certification. Consequently, the European Union Aviation Safety Agency (EASA) published a concept paper for machine learning applications in aviation. Both, the Concept of Operation (ConOps) in combination with an Operational Design Domain (ODD), are listed as objectives to be met for the safety analysis. From a developer{'}s perspective, this raises questions on how to effectively derive the ODD from ConOps and test the given system based on the ODD description. Based on an exemplary use case of a Near Mid-Air Collision avoidance between two aircraft through the advisories of ACAS X, a highly automated framework for generating and testing synthetic data is proposed. Using this framework, 1800 Near Mid-Air Collision scenario files are created and automatically executed in the simulation environment FlightGear. Scenario-based testing is used for the logging of ACAS X advisory data and evaluating it against predefined requirements. By this approach, an efficient way of verifying system requirements and conducting automated testing based on the ODD definition is demonstrated. Throughout this process, Model-Based Systems Engineering (MBSE) is used to reduce and manage complexity. The framework in this paper enables a systematic and highly automated approach for scenario generation based on the ODD.},
url = {https://elib.dlr.de/207924/},
keywords = {AI, Model-Based Systems Engineering, Operational Design Domain, Scenario-based testing}
}
R. Mut, G. Sauter, Y. Kees, F. Köster, und S. Hallerbach, "Adaptive Operational Design Domain" in Proc. Safetronic -International Conference on Holistic Safety for Road Vehicles, 2024.
@inproceedings{dlr212480, month = {November},
title = {Adaptive Operational Design Domain},
year = {2024},
note = {pages = 2},
booktitle = {Safetronic -International Conference on Holistic Safety for Road Vehicles},
author = {Mut, Ryan and Sauter, Gerald and Kees, Yannick and K{\"o}ster, Frank and Hallerbach, Sven},
keywords = {Adaptive Operational Design Domain},
url = {https://elib.dlr.de/212480/},
abstract = {As the development of the ODD in autonomous systems continue, it becomes imperative to uphold stringent safety measures. However, the landscape of autonomous systems poses unique challenges, including the need to ensure the safety of degraded or impaired systems. In response to this, we introduce a concept of the Adaptive Operational Design Domain (AODD) as a solution for insuring the safety and increasing the availability of a system. The Adaptive Operational Design Domain represents a significant advancement in the Operational Design Domain framework by introducing adaptability to accommodate impaired and degraded autonomous systems. The Adaptive Operational Design Domain aims not only to maintain safety but also to enhance system availability. By dynamically adjusting the Operational Design Domain based on real-time conditions of the system functionality and environment, Adaptive Operational Design Domain enables autonomous systems to operate safely, even when encountering partial impairment or degraded functionality.}
M. Nichting, D. Heß, und F. Köster, Maneuver-Level Cooperation of Automated VehiclesSpringer Cham.
@incollection{dlr206182,
author = {Nichting, Matthias and He{\ss},
Daniel and K{\"o}ster, Frank},
pages = {277--301},
editor = {Stiller, Christoph and Althoff, Matthias and Burger, Christoph and Deml, Barbara and Eckstein, Lutz and Flemisch, Frank},
publisher = {Springer Cham},
year = {2024},
title = {Maneuver-Level Cooperation of Automated Vehicles},
pages = {277--301},
booktitle = {Cooperatively Interacting Vehicles},
abstract = {Cooperative behavior of automated vehicles at the maneuver level is of utmost importance for the efficient and safe use of traffic space. This chapter discusses a vehicle-to-vehicle communication-based negotiation and cooperation method for maneuver cooperation. The method is based on the negotiation about explicitly defined reservation areas on the road for the exclusive use of a particular traffic participant. It covers all standard traffic situations occurring on regular streets and thus achieves universal applicability. The evaluation of simulations and driving tests shows the suitability of the method for effective maneuver cooperation in various traffic situations. Furthermore, based on this method, the planning and execution of cooperative maneuvers in emergency situations are investigated. Simulations show that collisions can be avoided in relevant cases by this method. Moreover, further simulations and driving tests show that joint maneuvers can avoid sharp braking maneuvers in many situations. In addition, research on a methodology for implicit maneuver cooperation is presented. Based on reinforcement learning methods, partially cooperative decision-making functions are studied in a setting that benefits from cooperative behavior. The evaluation shows that cooperative behaviors of road participants can be achieved using this technique.},
keywords = {Automated Driving, Cooperative Driving, V2X},
url = {https://elib.dlr.de/206182/}
}
M. Stäbler, F. Köster, C. Schluter-Langdon, und T. Müller, "Why an Automated, Scalable and Resilient Service for Semantic Interoperability is Needed" in Proc. SCITEPRESS Digital Library, 2024.
@inproceedings{dlr202041, booktitle = {SCITEPRESS Digital Library},
title = {Why an Automated, Scalable and Resilient Service for Semantic Interoperability is Needed},
note = {pages = 9},
year = {2024},
publisher = {SCITEPRESS Digital Library},
author = {St{\"a}bler, Maximilian and K{\"o}ster, Frank and Schluter-Langdon, Christoph and M{\"u}ller, Tobias},
month = {Februar},
keywords = {Semantic Landscape, Data Ecosystems, Data Spaces, Interoperability},
url = {https://elib.dlr.de/202041/},
abstract = {The increasing linkage of different data sources and data ecosystems underlines the need for high-quality and well-structured data. Unambiguous descriptions of data (meta-data) promote a common understanding of the data among different users. New ontologies and data schemas are constantly being developed for this purpose. While there are new ways to align, merge or match these ontologies and data schemas, the context of the data, which is important for a clear understanding, is often not taken into account. This work addresses this problem by analyzing a graph consisting of 1,615 data attributes from 13 domains and 828 different ontologies. The results show how overlapping and partially synonymous ontologies, both from the same domain and from different domains, are. The results show the complexity for users in creating unique descriptions of data and why new approaches and methods are needed to achieve semantic interoperability.}
}
M. Stäbler, F. Köster, C. Schluter-Langdon, und T. Müller, "Trust the Data You Use: Scalability Assurance Forms (SAF) for a Holistic Quality Assessment of Data Assets in Data Ecosystems" in Proc. 20th International Conference on Web Information Systems and Technologies, WEBIST (2024), 2024.
@inproceedings{dlr205678,
author = {St{\"a}bler, Maximilian and K{\"o}ster, Frank and Schluter-Langdon, Christoph and M{\"u}ller, Tobias},
series = {SCITEPRESS},
booktitle = {20th International Conference on Web Information Systems and Technologies, WEBIST (2024)},
year = {2024},
note = {pages = 12},
title = {Trust the Data You Use: Scalability Assurance Forms (SAF) for a Holistic Quality Assessment of Data Assets in Data Ecosystems},
publisher = {INSTICC},
abstract = {Companies generate terabytes of raw, unstructured data daily, which requires processing and organization to become valuable data assets. In the era of data-driven decision-making, evaluating these data assets' quality is crucial for various data services, users, and ecosystems. This paper introduces "Scalability Assurance Forms" (SAF), a novel framework to assess the quality of data assets, including raw data and semantic descriptions, with essential contextual information for cross-domain AI systems. The methodology includes a comprehensive literature review on quality models for linked data and knowledge graphs, and previous research findings on data quality. The SAF framework standardizes data asset quality assessments through 31 dimensions and 10 overarching groups derived from the literature. These dimensions enable a holistic assessment of data set quality by grouping them according to individual user requirements. The modular approach of the SAF framework ensures the maintenance of data asset quality across interconnected data sources, supporting reliable data-driven services and robust AI application development. The SAF framework addresses the need for trust in systems where participants may not know or historically trust each other, promoting the quality and reliability of data assets in diverse ecosystems.},
keywords = {Knowledge Graphs, Data Asset Quality, AI Systems Integration, Scalability Assurance Forms (SAF)},
url = {https://elib.dlr.de/205678/}
}
M. Stäbler, F. Köster, C. Schluter-Langdon, T. Guggenberger, D. Wang, und R. Mrasek, "Speaking the same language or automated translation? Designing semantic interoperability tools for Data Spaces" in Proc. 20th International Conference on Web Information Systems and Technologies, WEBIST (2024), 2024.
@inproceedings{dlr205682, booktitle = {20th International Conference on Web Information Systems and Technologies, WEBIST (2024)},
year = {2024},
title = {Speaking the same language or automated translation? Designing semantic interoperability tools for Data Spaces},
note = {pages = 12},
publisher = {INSTICC},
author = {St{\"a}bler, Maximilian and K{\"o}ster, Frank and Schluter-Langdon, Christoph and Guggenberger, Tobias and Wang, DanDan and Mrasek, Richard},
series = {SCITEPRESS},
url = {https://elib.dlr.de/205682/},
keywords = {Data Spaces, Semantic Interoperability, Design Principles, Data Ecosystem},
abstract = {This paper tackles the challenge of semantic interoperability in the ever-evolving data management and sharing landscape, crucial for integrating diverse data sources in cross-domain use cases. Our comprehensive approach, informed by an extensive literature review, focus-group discussions and expert insights from seven professionals, led to the formulation of six innovative design principles for interoperability tools in Data Spaces. These principles, derived from key meta-requirements identified through semi-structured interviews in a focus group, address the complexities of data heterogeneity and diversity. They offer a blend of automated, scalable, and resilient strategies, bridging theoretical and practical aspects to provide actionable guidelines for semantic interoperability in contemporary data ecosystems. This research marks a significant contribution to the domain, setting a new design approach for Data Space integration and management.}
}
T. Stefani, M. Jameel, I. Gerdes, R. Hunger, C. Bruder, E. Hoemann, J. M. Christensen, A. A. Girija, F. Köster, T. Krüger, und S. Hallerbach, "Towards an Operational Design Domain for Safe Human-AI Teaming in the Field of AI-Based Air Traffic Controller Operations" in Proc. 43rd AIAA DATC/IEEE Digital Avionics Systems Conference, DASC 2024, 2024.
@inproceedings{dlr207857, title = {Towards an Operational Design Domain for Safe Human-AI Teaming in the Field of AI-Based Air Traffic Controller Operations},
year = {2024},
booktitle = {43rd AIAA DATC/IEEE Digital Avionics Systems Conference, DASC 2024},
note = {pages = 10},
publisher = {IEEE},
author = {Stefani, Thomas and Jameel, Mohsan and Gerdes, Ingrid and Hunger, Robert and Bruder, Carmen and Hoemann, Elena and Christensen, Johann Maximilian and Girija, Akshay Anilkumar and K{\"o}ster, Frank and Kr{\"u}ger, Thomas and Hallerbach, Sven},
month = {September},
abstract = {Advances in Artificial Intelligence (AI) introduce both promising real-world applications in various fields such as aviation but also challenges in assuring safety. Regulators in aviation mandate, as with any other application, compliance of these AI-based systems with high safety standards. This especially holds for Human-AI Teaming. The European Union Aviation Safety Agency (EASA) outlined in their concept paper the definitions of cooperation and collaboration between humans and AI, as well as the differences in terms of authority and task allocation. Therein, the question of safety in situations of collaboration with shared goals, dynamic task allocation, and partial authority within the Human-AI team is paramount. As a safety concept, EASA requires the usage of Operational Design Domains (ODDs) from the automotive field. In this work, the concept of ODDs is transferred to the Air Traffic Control (ATC) domain. An initial ODD is defined for an AI-based digital team partner that supports Air Traffic Controllers in their daily work even for safety-critical tasks such as conflict detection and resolution. Additionally, the required tools for successfully executing this task is demonstrated. Based on the ODD description, conflict scenarios are generated and tested in a simulation environment, showcasing situations inside and outside the ODD. Based on these results, the feasibility of using ODDs in ATC is discussed, outlining a potential step towards the safe application of Human-AI Teaming.},
url = {https://elib.dlr.de/207857/},
keywords = {Operational Design Domain, AI Engineering, Human-AI Teaming, Air Traffic Control}
}
A. Anilkumar Girija, J. M. Christensen, T. Stefani, E. Hoemann, U. Durak, F. Köster, S. Hallerbach, und T. Krüger, "Towards the Monitoring of Operational Design Domains using Temporal Scene Analysis in the realm of Artificial Intelligence in Aviation" in Proc. 43rd AIAA DATC/IEEE Digital Avionics Systems Conference, DASC 2024, 2024.
@inproceedings{dlr207871,
author = {Anilkumar Girija, Akshay and Christensen, Johann Maximilian and Stefani, Thomas and Hoemann, Elena and Durak, Umut and K{\"o}ster, Frank and Hallerbach, Sven and Kr{\"u}ger, Thomas},
month = {November},
booktitle = {43rd AIAA DATC/IEEE Digital Avionics Systems Conference, DASC 2024},
year = {2024},
title = {Towards the Monitoring of Operational Design Domains using Temporal Scene Analysis in the realm of Artificial Intelligence in Aviation},
publisher = {IEEE},
note = {pages = 8},
url = {https://elib.dlr.de/207871/},
keywords = {Operational Design Domain, Evaluation, Safety, Scenario, AI Engineering},
abstract = {The application of Artificial Intelligence (AI) in aviation has gained significant attention in recent years, particularly in safety-critical domains such as aviation. One possible application in this domain is the next version of the Airborne Collision Avoidance System X (ACAS X). The current system, ACAS II, with its state-of-the-art implementation, TCAS II, has been in use for decades and has significantly reduced the number of mid-air collisions. However, it relies on a simple rule/heuristics-based logic, leading to false positives which increases the workload of both pilots and air traffic controllers unnecessarily. The next generation of collision avoidance systems, ACAS X, instead uses exhaustive lookup tables to determine resolution advisories. These lookup tables, however, are too large to be stored on current avionics hardware. Thus, neural networks can compress these lookup tables significantly, enabling the deployment of ACAS X on current avionics hardware. Nevertheless, deploying an AI-based system for predicting resolution advisories raises safety concerns regardless of whether it is used in commercial or unmanned aircraft. To mitigate these concerns, it is crucial to not only train the AI-based system on a substantial amount of data but also to understand and define the environmental conditions in which is supposed to operate. This concept is referred to as the Operational Design Domain (ODD). Monitoring ODD conditions is essential to ensure the safe operation of the AI-based system. This paper presents a novel methodology for predictive ODD monitoring, leveraging temporal scene analysis to assess potential scenarios that an AI-based system may encounter. Temporal scene analysis is a methodology that analyses scenarios by dividing them into discrete scenes, each representing a specific point in time within the scenario. This approach allows for a detailed examination of the scenario{'}s progression, identifying critical situations and transitions that may impact the AI-based system{'}s performance and safety. For this, it utilizes a database of scenarios generated based on the ODD description. Splitting the scenario into scenes and rearranging them to create new synthetic scenarios increases the data available for predictive ODD monitoring. All this will be demonstrated in the context of a collision avoidance use case.}
}
T. Stefani, J. M. Christensen, E. Hoemann, A. A. Girija, F. Köster, T. Krüger, und S. Hallerbach, "Applying Model-Based System Engineering and DEVOPS on the implementation of an AI-based collision avoidance system" in Proc. 34th Congress of the International Council of the Aeronautical Sciences, ICAS 2024, 2024.
@inproceedings{dlr207884,
author = {Stefani, Thomas and Christensen, Johann Maximilian and Hoemann, Elena and Girija, Akshay Anilkumar and K{\"o}ster, Frank and Kr{\"u}ger, Thomas and Hallerbach, Sven},
month = {September},
booktitle = {34th Congress of the International Council of the Aeronautical Sciences, ICAS 2024},
title = {Applying Model-Based System Engineering and DEVOPS on the implementation of an AI-based collision avoidance system},
note = {pages = 12},
year = {2024},
publisher = {DGLR},
abstract = {The implementation of Artificial Intelligence (AI) in the field of aviation promises significant improvements from assistance functions to a higher level of autonomy. The new Airborne Collision Avoidance System (ACAS X) is one example. However, as with any other technology in aviation, the implementation of artificial intelligence also needs to be strictly regulated to ensure the highest possible level of safety and security. The European Union Aviation Safety Agency (EASA) set the first regulatory framework, suggesting a W-model, which is placed on top of the well-known V-model, covering the dedicated requirements for the AI-system throughout the engineering process. Yet, this approach does not coincide fully with the established DevOps cycle from software engineering, which is increasingly being used for the development of AI-based systems. The early combination of development and operation stands in contrast to the linear approach of the W-model. To investigate AI-Engineering methodologies and the potential harmonization of both approaches, the example use case of collision avoidance is chosen. In this work, the AI-based ACAS XA and ACAS XU are implemented into a simulation environment and tested in scenarios avoiding multiple intruders. One horizontal and one vertical multi-collision avoidance scenario is executed demonstrating the implementation of the system-under-test as well as the successful collision avoidance. Throughout the engineering process from defining requirements down to the sub-system level, Model-Based System Engineering (MBSE) is used as an efficient way of handling the ever-increasing complexity of the engineering process and improving communication and understanding for all involved stakeholders.},
url = {https://elib.dlr.de/207884/},
keywords = {DevOps, AI-Based Systems, Collision Avoidance, Simulation-Enabled Engineering, MBSE}
}
J. M. Christensen, W. M. M. Zaeske, J. W. Beck, S. Friedrich, T. Stefani, A. Anilkumar Girija, E. Hoemann, U. Durak, F. Köster, T. Krüger, und S. Hallerbach, "Towards Certifiable AI in Aviation: A Framework for Neural Network Assurance Using Advanced Visualization and Safety Nets" in Proc. 43rd AIAA DATC/IEEE Digital Avionics Systems Conference, DASC 2024, 2024.
@inproceedings{dlr207941, pages = {1--9},
month = {November},
author = {Christensen, Johann Maximilian and Zaeske, Wanja Marlo Moritz and Beck, Janick Wolfgang and Friedrich, Sven and Stefani, Thomas and Anilkumar Girija, Akshay and Hoemann, Elena and Durak, Umut and K{\"o}ster, Frank and Kr{\"u}ger, Thomas and Hallerbach, Sven},
publisher = {IEEE},
title = {Towards Certifiable AI in Aviation: A Framework for Neural Network Assurance Using Advanced Visualization and Safety Nets},
year = {2024},
booktitle = {43rd AIAA DATC/IEEE Digital Avionics Systems Conference, DASC 2024},
keywords = {ACAS X, AI Engineering, Artificial Intelligence, Neural Networks, Safety},
url = {https://elib.dlr.de/207941/},
abstract = {While Artificial Intelligence (AI) has become an important asset in many areas of science and technology, safety is often not treated as important as required for aviation. Neglecting safety is not an option for aviation, where strict laws and regulations govern the certification process of new aircraft. Thus, a solid understanding of the underlying AI-based system is important to certify such systems. To this day, manual inspection by humans is an essential step for certification, however requires proper tooling. One such tool, called Advisory Viewer, is presented in this work, helping to break down the high-dimensional vector space of neural networks. The tool presented here can visualize decisions derived from assemblies of neural networks for arbitrary 2-dimensional parameter sweeps and provides real-time feedback upon any parameter change. It is designed to better understand the neural networks behind openCAS, an open-source implementation for the Airborne Collision Avoidance System X (ACAS X), the upcoming implementation for collision avoidance in aviation. However, as currently designed, implementing ACAS X is not feasible on current aviation hardware, as the required memory is not available. Here, neural networks and their ability to compress and generalize can be a solution. Therefore, it is of utmost importance that the AI-based system behind ACAS X always produces correct predictions. Finally, to fix the detected irregularities, this work implements a Safety Net to ensure the correct output for the ACAS X use case. Safety Nets are designed on the idea of sparse lookup tables (LUTs), storing only the points where the neural networks are known to fail. By deploying a system consisting of a Safety Net together with neural network(s), a small, yet potentially certifiable system can be designed and built. This work presents a generic data format for LUTs and recommended algorithms to populate and organize said LUTs for quick access during run-time. Combined, this serves as a generic framework for 100 \% assurance of small neural networks, joined by the visualization tooling for the specific use case of openCAS.}
}
J. M. Christensen, A. Anilkumar Girija, T. Stefani, U. Durak, E. Hoemann, F. Köster, T. Krüger, und S. Hallerbach, "Advancing the AI-Based Realization of ACAS X Towards Real-World Application" in Proc. 2024 IEEE 36th International Conference on Tools with Artificial Intelligence (ICTAI), 2024.
@inproceedings{dlr207945, publisher = {IEEE},
booktitle = {2024 IEEE 36th International Conference on Tools with Artificial Intelligence (ICTAI)},
title = {Advancing the AI-Based Realization of ACAS X Towards Real-World Application},
year = {2024},
pages = {57--64},
month = {Oktober},
author = {Christensen, Johann Maximilian and Anilkumar Girija, Akshay and Stefani, Thomas and Durak, Umut and Hoemann, Elena and K{\"o}ster, Frank and Kr{\"u}ger, Thomas and Hallerbach, Sven},
keywords = {Artificial Intelligence, ACAS X, Python, FlightGear},
url = {https://elib.dlr.de/207945/},
abstract = {In recent years, artificial intelligence (AI) has been applied to a wide range of safety-critical domains, such as automotive, robotics, and aviation. Especially the automotive and robotics domains have seen a rapid increase in the number of AI-based systems that are being deployed in real-world applications. However, real-world applications in the aviation domain are still sparse, given the challenges of AI engineering in combination with strict safety requirements. A first possible application of AI in the aviation domain might be the future collision avoidance system Airborne Collision Avoidance Systems X (ACAS X). The goal of collision avoidance systems is to issue advisories to the pilot to avoid near mid-air collisions (NMACs). The two important variants of ACAS X for this work are ACAS XA, providing vertical advisories and meant as a drop-in replacement for current systems in commercial air flight, and ACAS XU, providing horizontal advisories for the ever-growing unmanned aircraft systems market. This work brings both variants closer to real-world deployment by implementing a vertical collision avoidance system, based upon ACAS XA, and a horizontal collision avoidance system, based upon ACAS XU, for the research flight simulator FlightGear. Using advisories given by this implementation, this work furthermore provides an auto-avoid function that can command an airplane in FlightGear to safely avoid NMACs. Finally, this work will show that the ACAS X implementation can avoid collisions in a simulated environment. For this task, an Operational Design Domain will be defined serving as a basis for safety considerations and evaluating the implementation of the ACAS X. In the end, simulation-based testing will be used separately for VCAS and HCAS showing the successful utilization of advisory predictions as autopilot inputs. Summarizing, this work not only presents an open-source implementation of ACAS XA and ACAS XU for FlightGear but also shows how the generated advisories can be used to successfully avoid NMACs.}
}
F. Hanke, J. Unruh, M. Karl, und F. Köster, "Secure Dataspace Approach for Interorbital Satellite Links" in Proc. AIAA SciTech 2024 Forum, 2024.
@inproceedings{dlr202509, month = {Januar},
author = {Hanke, Felix and Unruh, Johannes and Karl, Michael and K{\"o}ster, Frank},
series = {AIAA 2024},
publisher = {AIAA},
note = {pages = 14},
booktitle = {AIAA SciTech 2024 Forum},
year = {2024},
title = {Secure Dataspace Approach for Interorbital Satellite Links},
url = {https://elib.dlr.de/202509/},
keywords = {Secure Dataspace, GAIA-X, Secure multiparty computation (MPC), Homomorphic encryption (HE), Satellite Communication},
abstract = {Satellite systems have a critical role in various domains such as communication, navigation, earth observation, and scientific research. Security of the data transmitted by satellite systems is of utmost importance to ensure the confidentiality, integrity, and availability of sensitive information. Satellite operators withhold orbital location data, despite the imperative to share information to avert collisions. In order to cope with these requirements, this proposed approach combines the concept of the GAIA-X data ecosystem with advanced privacy preserving techniques and decentralized computations. In order to do so, this paper uses technologies, such as secure multiparty computation (MPC) and homomorphic encryption (HE), to ensure data sovereignty for international collaboration in space missions. By sticking to the GAIA-X core values, this approach incorporates principles such as openness and transparency, federation, security-by-design and interoperability for an interorbital satellite link.}
}
M. Stäbler, P. Moosmann, P. Dittmer, D. Wang, C. Lange, und F. Köster, "Semantic Data Link: Bridging Domain-Specific Needs with Universal and Interoperable Semantic Models" in Proc. The Semantic Web : 21st International Conference, ESWC 2024, 2024.
@inproceedings{dlr204539, series = {Lecture Notes in Computer Science},
month = {Juni},
author = {St{\"a}bler, Maximilian and Moosmann, Paul and Dittmer, Patrick and Wang, DanDan and Lange, Christoph and K{\"o}ster, Frank},
publisher = {Springer Cham},
note = {pages = 9},
booktitle = {The Semantic Web : 21st International Conference, ESWC 2024},
title = {Semantic Data Link: Bridging Domain-Specific Needs with Universal and Interoperable Semantic Models},
year = {2024},
abstract = {The emergence of data-driven systems necessitates enhanced interoperability across diverse data ecosystems. Traditional approaches to semantic interoperability have been hindered by the complexity and specificity of ontologies, demanding significant expertise and resources for their development and maintenance. This paper introduces the Semantic Data Link (SDL) framework, a novel approach that aims to democratize data description and enhance semantic interoperability. SDL offers a domain and ontology-independent methodology, focusing on a multi-layered architecture that emphasizes decentralized semantics and categorizes data into definitional, structural, and contextual aspects. Developed as part of the Gaia-X 4 Future Mobility initiative, SDL is particularly pertinent to the mobility sector, where real-time data exchange and interoperability are crucial. This framework promises to bridge the gap between varying levels of expertise in semantic technologies and accelerate the development of semantically interoperable applications and services. We provide an in-depth discussion on the conceptual framework, design rationale, and implementation of SDL. The paper concludes with insights into the practical implications of SDL and prospective directions for future research in the quest for a seamless, interoperable data landscape.},
url = {https://elib.dlr.de/204539/},
keywords = {Semantic Interoperability, Data Ecosystems, Dataspaces, Domain Agnostic Framework}
}
Y. Kees, G. Sauter, R. Mut, B. Franke, K. Frank, und H. Sven, "ODD-based Health Monitoring and Predictive Maintenance of Degrading Vehicle Functionality" in Proc. Short Paper Proceedings of the 5th Workshop on Artificial Intelligence and Formal Verification, Logic, Automata, and Synthesis hosted by the 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2023), 2024.
@inproceedings{dlr199178, month = {Januar},
publisher = {CEUR Workshop Proceedings},
number = {3629},
booktitle = {Short Paper Proceedings of the 5th Workshop on Artificial Intelligence and Formal Verification, Logic, Automata, and Synthesis hosted by the 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2023)},
year = {2024},
note = {pages = 6},
title = {ODD-based Health Monitoring and Predictive Maintenance of Degrading Vehicle Functionality},
author = {Kees, Yannick and Sauter, Gerald and Mut, Ryan and Franke, Benedikt and Frank, K{\"o}ster and Sven, Hallerbach},
series = {Artificial Intelligence and Formal Verification, Logic, Automata, and Synthesis (OVERLAY)},
keywords = {Predictive Maintenance, Health Monitoring, Operational Design Domain (ODD), Degradation, Shock Absorber, Machine Learning},
url = {https://elib.dlr.de/199178/},
abstract = {The shock absorber of a vehicle is not only needed for a comfortable driving experience, but it is also essential for vehicle safety. Especially in autonomous driving, vehicles must monitor themselves and schedule maintenance before a component fails. In this work, we develop a methodology to predict the degradation of a shock absorber using machine learning methods and perform predictive maintenance recommendations. In the first step, we learn the damping coefficient from acceleration data using a neural network. Afterward, we extrapolate this value to predict future behavior. For this, we use the concept of operational design domains to formalize the point up until vehicle functionality is unrestricted and there is no risk to vehicle safety.}
M. Stäbler, F. Köster, und C. Schluter-Langdon, "Towards solving ontological dissonance using network graphs" in Proc. AMCIS 2023, 2023.
@inproceedings{dlr196554, title = {Towards solving ontological dissonance using network graphs},
publisher = {AIS eLibrary},
author = {St{\"a}bler, Maximilian and K{\"o}ster, Frank and Schluter-Langdon, Christoph},
year = {2023},
note = {pages = 5},
booktitle = {AMCIS 2023},
abstract = {Data Spaces are an emerging concept for the trusted implementation of data-based applications and business models, offering a high degree of flexibility and sovereignty to all stakeholders. As Data Spaces are currently emerging in different domains such as mobility, health or food, semantic interfaces need to be identified and implemented to ensure the technical interoperability of these Data Spaces. This paper consolidates data models from 13 different domains and analyzes the ontological dissonance of these domains. Using a network graph, central data models and ontology attributes are identified, while the semantic heterogeneity of these domains is described qualitatively. The research outlook describes how these results help to connect different Data Spaces across domains.},
keywords = {Data Spaces, Data Space Mesh, Semantic Interoperability, Ontology Dissonance, Semantic Mapping},
url = {https://elib.dlr.de/196554/}
}
T. Müller, M. Stäbler, H. Gascon, F. Köster, und F. Matthes, SoK: Assessing the State of Applied Federated Machine LearningCornell University.
@misc{dlr196452,
author = {M{\"u}ller, Tobias and St{\"a}bler, Maximilian and Gascon, Hugo and K{\"o}ster, Frank and Matthes, Florian},
year = {2023},
title = {SoK: Assessing the State of Applied Federated Machine Learning},
publisher = {Cornell University},
month = {August},
note = {pages = 9},
keywords = {Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Distributed, Parallel, and Cluster Computing (cs.DC)},
url = {https://elib.dlr.de/196452/},
abstract = {Machine Learning (ML) has shown significant potential in various applications; however, its adoption in privacy-critical domains has been limited due to concerns about data privacy. A promising solution to this issue is Federated Machine Learning (FedML), a model-to-data approach that prioritizes data privacy. By enabling ML algorithms to be applied directly to distributed data sources without sharing raw data, FedML offers enhanced privacy protections, making it suitable for privacy-critical environments. Despite its theoretical benefits, FedML has not seen widespread practical implementation. This study aims to explore the current state of applied FedML and identify the challenges hindering its practical adoption. Through a comprehensive systematic literature review, we assess 74 relevant papers to analyze the real-world applicability of FedML. Our analysis focuses on the characteristics and emerging trends of FedML implementations, as well as the motivational drivers and application domains. We also discuss the encountered challenges in integrating FedML into real-life settings. By shedding light on the existing landscape and potential obstacles, this research contributes to the further development and implementation of FedML in privacy-critical scenarios.}
}
M. L. Hickmann, A. P. Raulf, F. Köster, F. Schwenker, und H. Rieser, "Potential analysis of a Quantum RL controller in the context of autonomous driving" in Proc. 31st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2023, 2023.
@inproceedings{dlr198199, year = {2023},
booktitle = {31st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2023},
publisher = {Ciaco - i6doc.com},
pages = {263--268},
author = {Hickmann, Manuel Lautaro and Raulf, Arne Peter and K{\"o}ster, Frank and Schwenker, Friedhelm and Rieser, Hans-Martin},
editor = {Verleysen, Michel},
series = {ESANN 2023 proceedings},
title = {Potential analysis of a Quantum RL controller in the context of autonomous driving},
url = {https://elib.dlr.de/198199/},
keywords = {Quantum Machine Learning, Quantum Neural Networks, Reinforcement Learning, Quantum Reinforcement Learning, Autonomous Driving, Trajectory Planning, Variational Quantum Circuits},
abstract = {The potential of quantum enhanced Q-learning with a focus on its applicability to a lane change manoeuvre is investigated. In this context we solve multiple simple reinforcement learning environments using variational quantum circuits. The achieved results were similar to or even better than those of a simple constrained classical agent. We could observe promising behaviour on the more complex lane change manoeuvre task, which has an environment with an observation vector size twice larger than commonly used ones. For the Frozen Lake environment we found indications of possible quantum advantages in convergence rate.}
}
P. Lanz, A. Marino, M. D. Simpson, T. Brinkhoff, F. Köster, und M. Möller, "The InflateSAR Campaign: Developing Refugee Vessel Detection Capabilities with Polarimetric SAR" Remote Sensing, vol. 15, iss. 8.
@article{dlr195134,
author = {Lanz, Peter and Marino, Armando and Simpson, Morgan David and Brinkhoff, Thomas and K{\"o}ster, Frank and M{\"o}ller, Matthias},
journal = {Remote Sensing},
title = {The InflateSAR Campaign: Developing Refugee Vessel Detection Capabilities with Polarimetric SAR},
note = {pages = 27},
year = {2023},
number = {8},
volume = {15},
month = {April},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
note = {Mittelgeber: Nieders{\"a}chsisches Ministerium f{\"u}r Wissenschaft und Kultur, Interne Forschungsf{\"o}rderung der Jade HS Oldenburg},
keywords = {polarimetry (PolSAR); constant false alarm rate (CFAR) detector; polarimetric detector; sub-look detector; vessel-detection system (VDS); ship detection; synthetic aperture radar (SAR); disaster mitigation, refugee boat},
url = {https://elib.dlr.de/195134/},
abstract = {In the efforts to mitigate the ongoing humanitarian crisis at the European sea borders, this work builds detection capabilities to help find refugee boats in distress. For this paper, we collected dual-pol and quad-pol synthetic aperture radar (SAR) data over a 12 m rubber inflatable in a test-bed lake near Berlin, Germany. To consider a real scenario, we prepared the vessel so that its backscattering emulated that of a vessel fully occupied with people. Further, we collected SAR imagery over the ocean with different sea states, categorized by incidence angle and by polarization. These were used to emulate the conditions for a vessel located in ocean waters. This setup enabled us to test nine well-known vessel-detection systems (VDS), to explore the capabilities of new detection algorithms and to benchmark different combinations of detectors (detector fusion) with respect to different sensor and scene parameters (e.g., the polarization, wind speed, wind direction and boat orientation). This analysis culminated in designing a system that is specifically tailored to accommodate different situations and sea states.}
}
D. H. Le, K. Ihme, und F. Köster, "Involving users in Automotive HMI design: Design evaluation of an interactive simulation based on participatory design" in Proc. IHSI 2023 International Conference, 2023.
@inproceedings{dlr194093, title = {Involving users in Automotive HMI design: Design evaluation of an interactive simulation based on participatory design},
author = {Le, Duc Hai and Ihme, Klas and K{\"o}ster, Frank},
series = {Intelligent Human Systems Integration (IHSI 2023): Integrating People and Intelligent Systems},
note = {pages = 10},
volume = {69},
month = {Februar},
publisher = {Open Access Science in Human Factors Engineering and Human Centered Computing},
year = {2023},
booktitle = {IHSI 2023 International Conference},
abstract = {Abstract: User-centered design (UCD) methods for human-machine interfaces (HMI) have been a key to develop safe and user-friendly interaction for years. Especially in safety-critical domains like transportation, humans need to have clear instructions and feedback loops to safely interact with the vehicle. With the shift towards more automation on the streets, human-machine interaction needs to be predictable to ensure safe road interaction. Understanding human behavior and prior user needs in crucial situation can be significant in a multitude of complex interactions for in-vehicle passengers, pedestrians and other traffic participants.While research mostly focused on addressing user behavior and user needs, the inclusion of users has often been limited to study participants with behavioral inputs or interviewees prompted for opinions. Although users do not have the knowledge and experience as professional designers and experts to create a product for others alone, unbiased insights into the future target groups{'} mental models are a valuable and necessary asset. Hence, with stronger user participation and appropriate tools for users to design prototypes, the design process may deeper involve all type of stakeholders helping to provide insights into their mental models to understand user need and expectation.To extend current UCD practices in the development of automotive HMIs, our work introduces a user-interactive approach, based on the principles of participatory design (PD), to enable users to actively create and work within design process. A within-subject study was conducted based on evaluating users{'} trust within an interaction with an AV and subsequently configuring the corresponding HMI. The scenario focuses on the interaction between a pedestrian (user{'}s point of view) deciding to cross path with an automated vehicle (AV, SAE L4). The AV would show its intention via a 360-degree light band HMI on its roof. The interactive simulation offered users hands-on options to iteratively experience, evaluate and improve HMI elements within changeable environmental settings (i.e., weather, daytime) until they were satisfied with the result. The addition of participation was provided by an interface using common visual user interface elements, i.e. sliders and buttons, giving users a range of variety for real-time HMI configuring.A first prototype of this interactive simulation was tested for the safety-critical use-case in a usability study (N=29). Results from questionnaires and interviews show high usability acceptance of the interactive simulation among participants as assessed by the system usability scale. Overall usability was rated high (System Usability Scale) and frustration low (NASA-TLX raw). Moreover, the interactive simulation was rated to have above average user experience (User Experience Questionnaire). Appended feedback interviews gave valuable insights on improving the simulation user interface, offering different design opportunities within the simulation and a wider parameter space. The short design session time shows the limit of customizability options within this study but needs to be further investigated to determine optimal range for longer evaluation and design sessions. Based on the study results, further requirements for PD simulative environments to assess limits for parameter spaces in virtual environments are derived.},
url = {https://elib.dlr.de/194093/},
keywords = {Automotive, HMI, Human-Machine Interaction, HCI, MMI, Mensch-Maschine-Interaktion, Design, VR, Virtual Reality, Immersion, Participatory Design, PD, UCD, User-centered Design}
}
H. Rieser, F. Köster, und A. P. Raulf, "Tensor networks for quantum machine learning" Proceedings of the Royal Society a-Mathematical Physical and Engineering Sciences, vol. 479, iss. 2275.
@article{dlr196090,
author = {Rieser, Hans-Martin and K{\"o}ster, Frank and Raulf, Arne Peter},
journal = {Proceedings of the Royal Society a-Mathematical Physical and Engineering Sciences},
editor = {Hillston, Jane},
title = {Tensor networks for quantum machine learning},
note = {pages = 23},
number = {2275},
year = {2023},
month = {Juli},
volume = {479},
publisher = {The Royal Society},
abstract = {Once developed for quantum theory, tensor networks (TNs) have been established as a successful machine learning (ML) paradigm. Now, they have been ported back to the quantum realm in the emerging field of quantum ML to assess problems that classical computers are unable to solve efficiently. Their nature at the interface between physics and ML makes TNs easily deployable on quantum computers. In this review article, we shed light on one of the major architectures considered to be predestined for variational quantum ML. In particular, we discuss how layouts like matrix product state, projected entangled pair states, tree tensor networks and multi-scale entanglement renormalization ansatz can be mapped to a quantum computer, how they can be used for ML and data encoding and which implementation techniques improve their performance.},
url = {https://elib.dlr.de/196090/},
keywords = {tensor network, quantum machine learning, quantum computing, encoding}
}
L. Stepien, S. Hallerbach, und F. Köster, "Accelerating Simulation-Enabled Engineering" in Proc. 2022 IEEE International Symposium on Systems Engineering (ISSE), 2022.
@inproceedings{stepien2022accelerating, title={Accelerating Simulation-Enabled Engineering},
author={Stepien, Leonard and Hallerbach, Sven and K{\"o}ster, Frank},
booktitle={2022 IEEE International Symposium on Systems Engineering (ISSE)},
pages={1--8},
year={2022},
organization={IEEE}
}
L. Stepien und F. Köster, "Flexible Model Exchange in Modelling Smart Mobility by Using Domain Ontologies" in Proc. 2022 IEEE International Systems Conference (SysCon), 2022.
@inproceedings{stepien2022flexible, title={Flexible Model Exchange in Modelling Smart Mobility by Using Domain Ontologies},
author={Stepien, Leonard and K{\"o}ster, Frank},
booktitle={2022 IEEE International Systems Conference (SysCon)},
pages={1--7},
year={2022},
organization={IEEE}
}
K. F. S. Hallerbach U. Eberle, Simulation-Enabled Methods for the Development, Testing and Validation of Cooperative and Automated VehiclesZenodo.
@misc{dlr186897,
author = {S. Hallerbach, U. Eberle, F. K{\"o}ster},
journal = {Autonomes Fahren. Ein Treiber zuk{\"u}nftiger Mobilit{\"a}t},
month = {Februar},
title = {Simulation-Enabled Methods for the Development, Testing and Validation of Cooperative and Automated Vehicles},
publisher = {Zenodo},
year = {2022},
note = {pages 30--41}
L. Klitzke, K. Gimm, C. Koch, und F. Köster, "Extraction and Analysis of Highway On-Ramp Merging Scenarios from Naturalistic Trajectory Data" in Proc. 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), 2022.
doi: 10.1109/ITSC55140.2022.9922191
@INPROCEEDINGS{9922191,
author={Klitzke, Lars and Gimm, Kay and Koch, Carsten and Köster, Frank},
booktitle={2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)},
title={Extraction and Analysis of Highway On-Ramp Merging Scenarios from Naturalistic Trajectory Data},
year={2022},
volume={},
number={},
pages={654--660},
doi={10.1109/ITSC55140.2022.9922191}
}
P. Feifel, B. Franke, A. P. Raulf, F. Schwenker, F. Bonarens, und F. Köster, "Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection" in Proc. Proceedings of the Workshop on Artificial Intelligence Safety 2022 (AISafety 2022) co-located with the Thirty-First International Joint Conference on Artificial Intelligence and the Twenty-Fifth European Conference on Artificial Intelligence (IJCAI-ECAI-2022), Vienna, Austria, July 24-25, 2022, 2022.
@inproceedings{DBLP:conf/ijcai/FeifelFRSBK22,
author = {Patrick Feifel and Benedikt Franke and Arne P. Raulf and Friedhelm Schwenker and Frank Bonarens and Frank K{\"{o}}ster},
editor = {Gabriel Pedroza and Xin Cynthia Chen and Jos{\'{e}} Hern{\'{a}}ndez{-}Orallo and Xiaowei Huang and Hu{\'{a}}scar Espinoza and Richard Mallah and John A. McDermid and Mauricio Castillo{-}Effen},
title = {Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection},
booktitle = {Proceedings of the Workshop on Artificial Intelligence Safety 2022 (AISafety 2022) co-located with the Thirty-First International Joint Conference on Artificial Intelligence and the Twenty-Fifth European Conference on Artificial Intelligence (IJCAI-ECAI-2022), Vienna, Austria, July 24-25, 2022},
series = {{CEUR} Workshop Proceedings},
volume = {3215},
publisher = {CEUR-WS.org},
year = {2022},
url = {http://ceur-ws.org/Vol-3215/11.pdf},
timestamp = {Mon, 30 Jan 2023 11:25:04 +0100},
biburl = {https://dblp.org/rec/conf/ijcai/FeifelFRSBK22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
note = {10 pages}
}
V. Lizenberg, M. R. Alkurdi, U. Eberle, und F. Köster, "Intelligent Co-Simulation Framework for Cooperative Driving Functions" in Proc. ICCP: 17th International Conference on Intelligent Computer Communication and Processing, Cluj-Napoca, Romania, 2021.
@INPROCEEDINGS{Lizenberg2021IEEE,
author = {Lizenberg, Viktor and Alkurdi, Mhd Redwan and Eberle, Ulrich and K{\"o}ster, Frank},
title = {{I}ntelligent {C}o-{S}imulation {F}ramework for {C}ooperative {D}riving {F}unctions},
booktitle = {ICCP: 17th International Conference on Intelligent Computer Communication and Processing},
year = {2021},
address = {Cluj-Napoca, Romania},
publisher = {IEEE}
}
V. Lizenberg, D. Bischoff, Y. Haridy, U. Eberle, S. Knapp, und F. Köster, "Simulation-Based Evaluation of Cooperative Maneuver Coordination and its Impact on Traffic Quality" SAE International Journal of Advances and Current Practices in Mobility from WCX: World Congress Experience Digital Summit, vol. 3, iss. 6.
doi: 10.4271/2021-01-0171
@ARTICLE{Lizenberg2021SAE,
author = {Lizenberg, Viktor and Bischoff, Daniel and Haridy, Youssef and Eberle, Ulrich and Knapp, Steffen and K{\"o}ster, Frank},
title = {{S}imulation-{B}ased {E}valuation of {C}ooperative {M}aneuver {C}oordination and its {I}mpact on {T}raffic {Q}uality},
journal = {SAE International Journal of Advances and Current Practices in Mobility {from} WCX: World Congress Experience Digital Summit},
year = {2021},
volume = {3},
number = {6},
pages = {3159--3169},
note = {Technical Paper 2021-01-0171},
doi = {10.4271/2021-01-0171}
}
M. Nichting, T. Lobig, und F. Köster, "Case Study on Gap Selection for Automated Vehicles Based on Deep Q-Learning" in Proc. 2021 International Conference on Artificial Intelligence and Computer Science Technology (ICAICST), 2021.
doi: 10.1109/ICAICST53116.2021.9497818
@INPROCEEDINGS{9497818,
author={Nichting, Matthias and Lobig, Thomas and K{\"o}ster, Frank},
booktitle={2021 International Conference on Artificial Intelligence and Computer Science Technology (ICAICST)},
title={Case Study on Gap Selection for Automated Vehicles Based on Deep Q-Learning},
year={2021},
volume={},
number={},
pages={252-257},
doi={10.1109/ICAICST53116.2021.9497818}
}
L. Stepien und F. Köster, "Parametrizing Complex Co-Simulations to Support Decision Making in Mobility" in Proc. INFORMATIK 2021, 2021.
doi: 10.18420/informatik2021-015
@inproceedings{mci/Stepien2021,
author = {Stepien, Leonard and K{\"o}ster, Frank},
title = {Parametrizing Complex Co-Simulations to Support Decision Making in Mobility},
booktitle = {INFORMATIK 2021},
year = {2021},
editor = {} , pages = { 185-195 } , doi = {10.18420/informatik2021-015},
publisher = {Gesellschaft f{\"u}r Informatik, Bonn},
address = {}
}
Progress in Sustainable Mobility Research, Marx Gomez, J., Halberstadt, J., Henkel, A., Köster, F., Sauer, J., Taeger, J., Winter, A., und Woisetschläger, D. M. Eds., Springer.
doi: 10.1007/978-3-030-70841-2
@book{WinterGomez+2021nemo, editor = {Marx Gomez, Jorge and Halberstadt, Jantje and Henkel, Anna and K{\"o}ster, Frank and Sauer, J{\"u}rgen and Taeger, J{\"u}rgen and Winter, Andreas and Woisetschl{\"a}ger, David M.},
title = {Progress in Sustainable Mobility Research},
pages = {175},
publisher = {Springer},
isbn = {978-3-030-70840-5},
doi = {10.1007/978-3-030-70841-2},
year = {2021}
V. Lizenberg, B. Büchs, S. Knapp, R. Mannale, und F. Köster, "Graphical Data Visualization for Vehicular Communication Systems in Real and Virtual Test Environments" in Proc. AmE: Automotive meets Electronics (11th GMM-Symposium), Dortmund, Germany, 2020.
@INPROCEEDINGS{Lizenberg2020AmE,
author = {Lizenberg, Viktor and B{\"u}chs, Bernd and Knapp, Steffen and Mannale, Roman and K{\"o}ster, Frank},
title = {{G}raphical {D}ata {V}isualization for {V}ehicular {C}ommunication {S}ystems in {R}eal and {V}irtual {T}est {E}nvironments},
booktitle = {AmE: Automotive meets Electronics (11th GMM-Symposium)},
address = {Dortmund, Germany},
pages = {65--70},
publisher = {VDE Verlag GmbH},
month = {10--11 March},
year = {2020}
}
L. Klitzke, C. Koch, und F. Köster, "Identification of Lane-Change Maneuvers in Real-World Drivings with Hidden Markov Model and Dynamic Time Warping" in Proc. 23rd Intelligent Transportation Systems Conference (IEEE ITSC 2020), 2020.
@inproceedings{dlr135748, year = {2020},
journal = {IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC},
author = {Lars Klitzke and Carsten Koch and Frank K{\"o}ster},
title = {Identification of Lane-Change Maneuvers in Real-World Drivings with Hidden Markov Model and Dynamic Time Warping},
booktitle = {23rd Intelligent Transportation Systems Conference (IEEE ITSC 2020)},
keywords = {Lane-change Maneuver, Hidden Markov Model, Dynamic Time Warping, Divisive Hierarchical Clustering, Automated Driving},
url = {https://elib.dlr.de/135748/},
note = {7 pages},
abstract = {For the introduction of new automated driving functions, the systems need to be verified extensively. A scenario-driven approach has become an accepted method for this task. But to verify the functionality of an automated vehicle in the simulation in a certain scenario such as a lane change, relevant characteristics of scenarios need to be identified. This, however, requires to extract these scenarios from real-world drivings accurately. For that purpose, this work proposes a novel framework based on a set of unsupervised learning methods to identify lane-changes on motorways. To represent various types of lane changes, the maneuver is split up into primitive driving actions with an Hidden Markov Model and Divisive Hierarchical Clustering. Based on this, lane change maneuvers are identified using Dynamic-Time-Warping. The presented framework is evaluated with a real-world test drive and compared to other baseline methods. With a f1 score of 98.01{$\backslash$}\% in lane-change identification, the presented approach shows promising results.}
}
M. Nichting, D. Heß, J. Schindler, T. Hesse, und F. Köster, "Space Time Reservation Procedure (STRP) for V2X-Based Maneuver Coordination of Cooperative Automated Vehicles in Diverse Conflict Scenarios" in Proc. 2020 IEEE Intelligent Vehicles Symposium (IV), 2020.
doi: 10.1109/IV47402.2020.9304769
@INPROCEEDINGS{9304769,
author={Nichting, Matthias and He{\ss},
Daniel and Schindler, Julian and Hesse, Tobias and K{\"o}ster, Frank},
booktitle={2020 IEEE Intelligent Vehicles Symposium (IV)},
title={Space Time Reservation Procedure (STRP) for V2X-Based Maneuver Coordination of Cooperative Automated Vehicles in Diverse Conflict Scenarios},
year={2020},
volume={},
number={},
pages={502-509},
doi={10.1109/IV47402.2020.9304769}
}
F. Köster, C. Linder, und C. Sontag, Datenarchitekturen fahrzeuggenerierter Daten. Studie im Auftrag des Bundesministeriums für Wirtschaft und Energie - Endbericht.
@misc{KoFDLR,
author = {K{\"o}ster, Frank and Christian Linder and Christopher Sontag},
title = {Datenarchitekturen fahrzeuggenerierter Daten. Studie im Auftrag des Bundesministeriums f{\"u}r Wirtschaft und Energie - Endbericht},
pages = {1-36} , month = {Februar},
year = {2020}
}
C. Hungar, S. Jürgens, D. Wilbers, und F. Köster, "Map-Based Localization with Factor Graphs for Automated Driving using Non-Semantic LiDAR Features" in Proc. 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), 2020.
doi: 10.1109/ITSC45102.2020.9294726
@INPROCEEDINGS{9294726,
author={Hungar, Constanze and J{\"u}rgens, Stefan and Wilbers, Daniel and K{\"o}ster, Frank},
booktitle={2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)},
title={Map-Based Localization with Factor Graphs for Automated Driving using Non-Semantic LiDAR Features},
year={2020},
volume={},
number={},
pages={1-6},
doi={10.1109/ITSC45102.2020.9294726}
V. Lizenberg, S. Knapp, R. Mannale, V. Wendel, und F. Köster, "Simulationsbasierte Bewertungs- und Vergleichsmethodik für Abstimmungsverfahren in kooperativen Fahrfunktionen" in Proc. AAET: Automatisiertes und vernetztes Fahren, Braunschweig, Germany, 2019.
@INPROCEEDINGS{Lizenberg2019AAET,
author = {Lizenberg, Viktor and Knapp, Steffen and Mannale, Roman and Wendel, Viktor and K{\"o}ster, Frank},
title = {{S}imulationsbasierte {B}ewertungs- und {V}ergleichsmethodik f{\"u}r {A}bstimmungsverfahren in kooperativen {F}ahrfunktionen},
booktitle = {AAET: Automatisiertes und vernetztes Fahren},
address = {Braunschweig, Germany},
pages = {48--65},
publisher = {ITS mobility e.V.},
month = {6--7 February},
year = {2019}
}
C. Hungar, F. Köster, und S. Jürgens, "Ein Beitrag zur kartenbasierten Positionierung von Fahrzeugen mittels Mustererkennung in LiDAR-Daten" in Proc. AAET: Automatisiertes und vernetztes Fahren, Braunschweig, Germany, 2019.
@INPROCEEDINGS{HungaretAl,
author = {C. Hungar and F. K{\"o}ster and S. J{\"u}rgens},
title = {Ein Beitrag zur kartenbasierten Positionierung von Fahrzeugen mittels Mustererkennung in LiDAR-Daten},
booktitle = {AAET: Automatisiertes und vernetztes Fahren},
address = {Braunschweig, Germany},
pages = {135-155},
month = {5--7 February},
year = {2019}
}
D. Heß, S. Lapoehn, F. Utesch, M. Fischer, J. Schindler, T. Hesse, und F. Köster, "Contributions of the EU Projects UnCoVerCPS and Enable-S3 to Highly Automated Driving in Conflict Situations" in Proc. AAET: Automatisiertes und vernetztes Fahren, Braunschweig, Germany, 2019.
@INPROCEEDINGS{HessetAl,
author = {D. He{\ss} and S. Lapoehn and F. Utesch and M. Fischer and J. Schindler and T. Hesse and F. K{\"o}ster},
title = {Contributions of the EU Projects UnCoVerCPS and Enable-S3 to Highly Automated Driving in Conflict Situations},
booktitle = {AAET: Automatisiertes und vernetztes Fahren},
address = {Braunschweig, Germany},
pages = {92-117},
month = {5--7 February},
year = {2019}
}
J. Eilbrecht, D. Heß, F. Köster, und O. Stursberg, "Sichere Trajektorienplanung für autonome Fahrzeuge unter Verwendung steuerbarer und erreichbarer Mengen" in Proc. AAET: Automatisiertes und vernetztes Fahren, Braunschweig, Germany, 2019.
@INPROCEEDINGS{EilbrechtetAl,
author = {J. Eilbrecht and D. He{\ss} and F. K{\"o}ster and O. Stursberg},
title = {Sichere Trajektorienplanung f{\"u}r autonome Fahrzeuge unter Verwendung steuerbarer und erreichbarer Mengen},
booktitle = {AAET: Automatisiertes und vernetztes Fahren},
address = {Braunschweig, Germany},
pages = {66-91},
month = {5--7 February},
year = {2019}
}
L. Klitzke, C. Koch, A. Haja, und F. Köster, "Real-world Test Drive Vehicle Data Management System for Validation of Automated Driving Systems" in Proc. Proceedings of the 5th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, 2019.
doi: 10.5220/0007720501710180
@INPROCEEDINGS{vehits19,
author={Lars Klitzke and Carsten Koch and Andreas Haja and Frank K{\"o}ster},
title={Real-world Test Drive Vehicle Data Management System for Validation of Automated Driving Systems},
booktitle={Proceedings of the 5th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS},
year={2019},
pages={171-180},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007720501710180},
isbn={978-989-758-374-2}
}
C. Hungar, S. Brakemeier, S. Jürgens, und F. Köster, "GRAIL: A Gradients-of-Intensities-based Local Descriptor for Map-based Localization Using LiDAR Sensors" in Proc. Proceedings of IEEE Conference on Intelligent Transportation Systems (ITSC), 2019.
doi: 10.1109/ITSC.2019.8917525
@INPROCEEDINGS{chungaretAl,
author={C. Hungar and S. Brakemeier and S. J{\"u}rgens and F. K{\"o}ster},
title={GRAIL: A Gradients-of-Intensities-based Local Descriptor for Map-based Localization Using LiDAR Sensors},
booktitle={Proceedings of IEEE Conference on Intelligent Transportation Systems (ITSC)},
year={2019},
month = {October},
pages={4398-4403},
publisher={IEEE},
doi={10.1109/ITSC.2019.8917525}
}
L. Klitzke, J. Meyer, T. Leune, C. Koch, und F. Köster, "DAGMaR: A DAG-based Robust Road Membership Estimation Framework for Scenario Mining" in Proc. Sixth International Conference on Internet of Things: Systems, Management and Security (IOTSMS), 2019.
doi: 10.1109/IOTSMS48152.2019.8939213
@INPROCEEDINGS{klitzkeetAl,
author={L. Klitzke and J. Meyer and T. Leune and C. Koch and F. K{\"o}ster},
title={DAGMaR: A DAG-based Robust Road Membership Estimation Framework for Scenario Mining},
booktitle={Sixth International Conference on Internet of Things: Systems, Management and Security (IOTSMS)},
year={2019},
month = {October},
pages={358-365},
publisher={IEEE},
doi={10.1109/IOTSMS48152.2019.8939213}
}
C. Hungar, J. Fricke, J. S., und F. Köster, "Detection of Feature Areas for Map-based Localization Using LiDAR Descriptors" in Proc. 16th IEEE Workshop on Positioning, Navigation and Communications (WPNC), Bremen, Germany, 2019.
@INPROCEEDINGS{FricketAl,
author = {C. Hungar and J. Fricke and S. J{\"u}rgens and F. K{\"o}ster},
title = {Detection of Feature Areas for Map-based Localization Using LiDAR Descriptors},
booktitle = {16th IEEE Workshop on Positioning, Navigation and Communications (WPNC)},
address = {Bremen, Germany},
note = {6 pages},
month = {October},
year = {2019}
}
F. Köster und J. Mazzega, "Testfeld Niedersachsen - Bausteine und Anwendungsmöglichkeiten" in Proc. B.H. Oppermann, J. Stender-Vorwachs. Autonomes Fahren - Technische Grundlagen, Rechtsprobleme, Rechtsfolgen, 2019.
@INPROCEEDINGS{KoesteretAl,
author = {F. K{\"o}ster and J. Mazzega},
title = {Testfeld {N}iedersachsen - {B}austeine und {A}nwendungsm{\"o}glichkeiten},
booktitle = {B.H. Oppermann, J. Stender-Vorwachs. Autonomes Fahren - Technische Grundlagen, Rechtsprobleme, Rechtsfolgen},
edition ={2. Auflage},
publisher = {C.H. BECK},
pages = {31--38},
month= {November},
year = {2019}
}
M. Nichting, D. Heß, J. Schindler, T. Hesse, und F. Köster, "Explicit Negotiation Method for Cooperative Automated Vehicles" in Proc. 2019 IEEE International Conference on Vehicular Electronics and Safety (ICVES), 2019.
doi: 10.1109/ICVES.2019.8906401
@INPROCEEDINGS{8906401,
author={Nichting, Matthias and He{\ss},
Daniel and Schindler, Julian and Hesse, Tobias and K{\"o}ster, Frank},
booktitle={2019 IEEE International Conference on Vehicular Electronics and Safety (ICVES)},
title={Explicit Negotiation Method for Cooperative Automated Vehicles},
year={2019},
volume={},
number={},
pages={1-7},
doi={10.1109/ICVES.2019.8906401}
S. Hallerbach, Y. Xia, U. Eberle, und F. Köster, "Simulation-Based Identifcation of Critical Scenarios for Cooperative and Automated Vehicles" SAE International Journal of Connected and Automated Vehicles.
@article{dlr125759, month = {Dezember},
title = {Simulation-Based Identifcation of Critical Scenarios for Cooperative and Automated Vehicles},
author = {Sven Hallerbach and Yiqun Xia and Ulrich Eberle and Frank K{\"o}ster},
publisher = {SAE International},
year = {2018},
pages = {93--106},
journal = {SAE International Journal of Connected and Automated Vehicles},
keywords = {Automated vehicles, Cooperative vehicles, Simulators, Test facilities, Test procedures, Simulation and modeling, Identification and verifcation, Simulation-based testing, Automotive engineering, Traffic quality},
url = {https://elib.dlr.de/125759/},
abstract = {One of the major challenges for the automotive industry will be the release and validation of cooperative and automated vehicles. The immense driving distance that needs to be covered for a conventional validation process requires the development of new testing procedures. Further, due to limited market penetration in the beginning, the driving behavior of other human trafc participants, regarding a mixed trafc environment, will have a signifcant impact on the functionality of these vehicles. In this article, a generic simulation-based toolchain for the model-in-the-loop identifcation of critical scenarios will be introduced. The proposed methodology allows the identifcation of critical scenarios with respect to the vehicle development process. The current development status of the cooperative and automated vehicle determines the availability of testable simulation models, software, and components. The identifcation process is realized by a coupled simulation framework. A combination of a vehicle dynamics simulation that includes a digital prototype of the cooperative and automated vehicle, a trafc simulation that provides the surrounding environment, and a cooperation simulation including cooperative features is used to establish a suitable comprehensive simulation environment. The behavior of other trafc participants is considered in the trafc simulation environment. The criticality of the scenarios is determined by appropriate metrics. Within the context of this article, both standard safety metrics and newly developed trafc quality metrics are used for evaluation. Furthermore, we will show how the use of these new metrics allows for investigating the impact of cooperative and automated vehicles on trafc. The identifed critical scenarios are used as an input for X-in-the-Loop methods, test benches, and proving ground tests to achieve an even more precise comparison to real-world situations. As soon as the vehicle development process is in a mature state, the digital prototype becomes a {``}digital twin{''} of the cooperative and automated vehicle.}
}
D. Heß, R. Lattarulo, P. Joshue, S. Julian, H. Tobias, und K. Frank, "Fast Maneuver Planning for Cooperative Automated Vehicles" in Proc. 21st IEEE International Conference on Transportation Systems, 2018.
@inproceedings{dlr119834, booktitle = {21st IEEE International Conference on Transportation Systems},
month = {November},
title = {Fast Maneuver Planning for Cooperative Automated Vehicles},
author = {Daniel He{\ss} and Ray Lattarulo and P{\'e}rez Joshue and Schindler Julian and Hesse Tobias and K{\"o}ster Frank},
year = {2018},
keywords = {Cooperative Automated Driving, Motion Planning, Vehicle to Vehicle Communication, V2V, QP, STRP},
url = {https://elib.dlr.de/119834/},
pages = {1625--1632},
abstract = {A lane following and lane changing maneuver planning method for automated vehicles is investigated, which is capable of evaluating and incorporating cooperative agreements between several automated vehicles. An application level cooperation protocol is discussed, which allows vehicles to negotiate space time reservations in conflict areas via Vehicle-to-Vehicle communication. The planning method is based on decoupling of longitudinal and lateral movement directions, formulation of convex quadratic programming problems and input-output linearization for recovery of a full state reference trajectory and feed forward controls. Several different lane following and merging maneuvers can be planned in one update cycle in order to support an informed selection of the currently best driving strategy. We demonstrate and evaluate the communication protocol and the maneuver planning method on cooperative lane changing scenarios with a physical automated vehicle as well as in a real time simulation.}
}
H. Hungar und F. Köster, "Formalisierung von Szenario-Klassen zur Absicherung automatisierter Fahrfunktionen" in Proc. AAET 2018: Automatisiertes und vernetztes Fahren, 2018.
@inproceedings{dlr125272,
author = {Hardi Hungar and Frank K{\"o}ster},
note = {Bezug zu dem BMWi-Projekt PEGASUS (2016-2019)},
booktitle = {AAET 2018: Automatisiertes und vernetztes Fahren},
editor = {ITS mobility e. V.},
title = {Formalisierung von Szenario-Klassen zur Absicherung automatisierter Fahrfunktionen},
journal = {AAET 2018: Automatisiertes und vernetztes Fahren},
pages = {97--114},
year = {2018},
keywords = {Automatisiertes Fahren, Testspezifikation, Testen},
url = {https://elib.dlr.de/125272/},
abstract = {Um die Sicherheit automatisierter Fahrfunktion nachzuweisen, ist es erforderlich, systematisch alle potentiell kritischen Situationen zu erfassen, in welcher die Fahrfunktion im Betrieb zuverl{\"a}ssig agieren muss. Die hohe Anzahl der relevanten Situationen macht eine maschinelle Behandlung erforderlich. Deshalb m{\"u}ssen sie formalisiert beschrieben werden, so dass Testf{\"a}lle automatisch abgeleitet werden k{\"o}nnen. Diese Arbeit stellt einen Ansatz f{\"u}r eine solche Formalisierung vor. Basis der Beschreibungen sind Man{\"o}ver von Verkehrsteilnehmern, die zu Ablaufstrukturen zusammengesetzt werden. Die verschiedenen konkreten Auspr{\"a}gungen der Ablaufstrukturen ergeben die Testf{\"a}lle.}
}
S. Hallerbach, U. Eberle, und F. Köster, AAET 2017: Absicherungs- und Bewertungsmethoden für kooperative hochautomatisierte Fahrzeuge.
@misc{hallerbachAAET17, month = {Februar},
title = {AAET 2017: Absicherungs- und Bewertungsmethoden f{\"u}r kooperative hochautomatisierte Fahrzeuge},
author = {Hallerbach, Sven and Eberle, Ulrich and K{\"o}ster, Frank},
year = {2017}
}
S. Hallerbach, U. Eberle, und F. Köster, AmE 2017: The challenges of releasing cooperative and highly automated vehicles -- A look beyond functional requirements.
@misc{hallerbachAmE17, month = {M{\"a}rz},
title = {AmE 2017: The challenges of releasing cooperative and highly automated vehicles -- A look beyond functional requirements},
author = {Hallerbach, Sven and Eberle, Ulrich and K{\"o}ster, Frank},
year = {2017}
}
K. Preuk, M. Dotzauer, F. Köster, und M. Jipp, Encounters Between Drivers with and without Cooperative Intelligent Transport SystemsSpringer Verlag.
@incollection{dlr103398, editor = {Klaus Bengler and Julia Dr{\"u}ke and Silja Hoffmann and Dietrich Manstetten and Alexandra Neukum},
title = {Encounters Between Drivers with and without Cooperative Intelligent Transport Systems},
author = {Katharina Preuk and Mandy Dotzauer and Frank K{\"o}ster and Meike Jipp},
publisher = {Springer Verlag},
year = {2017},
pages = {363--377},
journal = {UR:BAN Human Factors in Traffic},
keywords = {Human Factors, Urban Traffic, MoSAIC, Multi-Driver Simulation},
url = {http://elib.dlr.de/103398/}
}
B. Schürmann, D. Heß, J. Eilbrecht, O. Stursberg, F. Köster, und M. Althoff, "Ensuring Drivability of Planned Motions from Simple Models Using Formal Methods" in Proc. ITSC 2017, 2017.
@inproceedings{dlr111510, booktitle = {ITSC 2017},
title = {Ensuring Drivability of Planned Motions from Simple Models Using Formal Methods},
author = {Bastian Sch{\"u}rmann and Daniel He{\ss} and Jan Eilbrecht and Olaf Stursberg and Frank K{\"o}ster and Matthias Althoff},
year = {2017},
keywords = {Automated Driving, Conformance Testing, Reachability Analysis, Formal Verification},
url = {http://elib.dlr.de/111510/},
abstract = {Motion planning of automated vehicles requires dynamical models to ensure that obtained trajectories are drivable. An often overlooked aspect is that usually simplified models are used for motion planning, which do not always sufficiently conform to the real behavior of vehicles. Thus, collision avoidance and drivability is not necessarily ensured. We address this problem by modeling vehicles as differential inclusions composed from simple dynamics plus set-based uncertainty; conformance testing is used to determine the required uncertainty. To quickly provide the set of solutions of these uncertain models, we provide pre-computed reachable sets (i.e. union of all possible solutions) for pre-selected motion primitives. The reachable sets of vehicles are obtained by a novel combination of optimization techniques and reachability analysis {--} they enable us to guarantee safety by checking their mutual non-intersection for consecutive time intervals. The benefits of our approach are demonstrated by numerical experiments.}
}
M. Dotzauer, S. Knake-Langhorst, und F. Köster, Understanding interactions between bicyclists and motorists in intersectionsSpringer.
@incollection{dlr104172,
author = {Mandy Dotzauer and Sascha Knake-Langhorst and Frank K{\"o}ster},
series = {ATZ/MTZ- Fachbuch},
editor = {Klaus Bengler and Slija Hoffmann and Dietrich Manstetten and Alexandra Neukum and Julia Dr{\"u}ke},
title = {Understanding interactions between bicyclists and motorists in intersections},
publisher = {Springer},
journal = {UR:BAN Human Factors in Traffic},
pages = {311--324},
year = {2017},
keywords = {cooperation, bicyclist-motorist-interaction, oberservation, intersections},
url = {http://elib.dlr.de/104172/},
abstract = {Especially in urban areas, more people began choosing the bicycle over the car in order to get from point A to point B. On the downside, more bicyclist in the streets resulted in a 50 percent increase of fatalities. Last year, in Germany, bicyclist accounted for twelve percent of all fatalities. Research shows that a major contributing factor to those fatalities is {`}insufficient cooperation{'} between cyclists and motorists. Nonetheless, most encounters of bicyclists and motorists neither result in conflicts nor in fatal crashes. In order to investigate interaction patterns between bicyclists and motorists, those road users were observed at a busy intersection in Braunschweig for a period of 10 working days. Situations, recorded at AIM research intersection, in which motorists turned right and bicyclists went straight through the intersection, were analyzed. The goal was to understand the behavior and the underlying mechanism, quantify the observed behavior, and identify objective parameters to map the behavior. As a result, the knowledge may be used to implement strategies and technology that may predict and prevent fatal crashes in intersections.}
J. Schindler und F. Köster, "A Model-Based Approach for Performing Successful Multi-Driver Scenarios" in Proc. The Driving Simulation Conference 2016 VR, 2016.
@inproceedings{dlr102754, month = {September},
author = {Julian Schindler and Frank K{\"o}ster},
booktitle = {The Driving Simulation Conference 2016 VR},
editor = {Andras Kemeny and Fr{\'e}d{\'e}ric M{\'e}rienne and Florent Colombet and St{\'e}phane Espi{\'e}},
title = {A Model-Based Approach for Performing Successful Multi-Driver Scenarios},
journal = {Proceedings of the DSC 2016 Europe},
pages = {93--97},
year = {2016},
keywords = {Model-Based Scenario Design; Multi-Driver; MoSAIC; Bayesian Networks},
url = {http://elib.dlr.de/102754/},
abstract = {When designing driving simulator studies, sometimes high efforts have to be spent to make them successful. Some drivers may not behave as desired, leading to situations unforeseen by the developers. When looking at multi-driver studies, where multiple drivers need to interact with each other in one virtual environment, the probability of performing a successful study is even lower, as the behaviour of the human drivers cannot be fully controlled. While [Oel15b] already proposed guidelines for the creation of such scenarios, this paper describes how the probability of success can be monitored and even enhanced during scenario execution. Therefore, it describes an approach where the probability of success is modelled and where the scenario is dynamically adapted to provide higher rates of success.}
}
F. Köster, "Anwendungsplattform für Intelligente Mobilität - Dienstspektrum und Architektur" ZEVrail - Zeitschrift für das gesamte System Bahn, vol. 8.
@article{dlr106220, volume = {8},
month = {August},
author = {Frank K{\"o}ster},
editor = {Hans-Peter Dipl.-Ing. Lang and Olaf Naujoks and Christian Prof.Dr.-Ing. Schindler and Peter Univ.-Prof.Dipl.-Ing.Dr.techn. Veit},
title = {Anwendungsplattform f{\"u}r Intelligente Mobilit{\"a}t - Dienstspektrum und Architektur},
publisher = {Georg Siemens Verlag},
year = {2016},
journal = {ZEVrail - Zeitschrift f{\"u}r das gesamte System Bahn},
pages = {276--282},
keywords = {AIM, Fahrzeugautomatisierung, kooperative Fahrzeug-/Infrastruktursysteme, Verkehrsfluss, Multimodale Mobilit{\"a}t},
url = {http://elib.dlr.de/106220/},
abstract = {Mit der seit 2014 operativen Anwendungsplattform f{\"u}r Intelligente Mobilit{\"a}t (AIM) verf{\"u}gt das Deutsche Zentrum f{\"u}r Luft- und Raumfahrt e.V. (DLR) in Braunschweig (Niedersachsen) {\"u}ber eine einzigartige Gro{\ss}forschungsanlage f{\"u}r Akteure aus Wissenschaft und Wirtschaft im Bereich der intelligenten Mobilit{\"a}tsdienste, dies sind z.B. Fahrzeughersteller, Zulieferer, Anbieter von Verkehrsmanagementl{\"o}sungen, Service-Provider im Feld der Verkehrslageinformationen, Universit{\"a}ten und andere wissenschaftliche Einrichtungen. AIM unterst{\"u}tzt Forschungs- und Entwicklungsprojekte durch eine umfangreiche generische Infrastruktur in Laboren, auf Testgel{\"a}nden und im {\"o}ffentlichen Raum, die sowohl Arbeiten mit hohem systemischen Anspruch als auch einer herausragenden fachlichen Tiefe erm{\"o}glicht. Anwendungsschwerpunkte liegen zum Beispiel in den Bereichen Fahrzeugautomatisierung, kooperative Fahrzeug-/Infrastruktursysteme, Verkehrsfluss und inter- sowie multimodale Mobilit{\"a}t. In diesen Bereichen werden auch Arbeiten zur Markteinf{\"u}hrung und Migration unterst{\"u}tzt. F{\"u}r die Ableitung neuartiger L{\"o}sungsans{\"a}tze im Bereich Verkehr kann AIM die Anforderungsermittlung und Systemevaluation unterst{\"u}tzen, wobei auch auf Informationen zum allgemeinen Mobilit{\"a}tsverhalten zur{\"u}ckgegriffen werden kann.}
}
J. Weimer, S. Schmid, M. Schier, F. Rinderknecht, G. Kopp, F. Köster, und T. Bünte, "Next Generation Car -- Technologies for future EVs" in Proc. EVS29, 2016.
@inproceedings{dlr105078, booktitle = {EVS29},
month = {Juni},
title = {Next Generation Car {--} Technologies for future EVs},
author = {J{\"u}rgen Weimer and Stephan Schmid and Michael Schier and Frank Rinderknecht and Gerhard Kopp and Frank K{\"o}ster and Tilman B{\"u}nte},
year = {2016},
journal = {Electric Vehicle Symposium EVS29 Montr{\'e}al, Qu{\'e}bec, Canada, June 19-22, 2016},
keywords = {car, van, hydrogen, EV (electric vehicle), ZEV (zero emission vehicle), multidisciplinary},
url = {http://elib.dlr.de/105078/},
abstract = {The German Aerospace Center has merged a wide range of technological research and development for future cars in a meta-project called {``}Next Generation Car{''}. Within this large research project technologies for three vehicle concepts for different applications (urban, regional and interurban), and with different powertrains (fuel-cell, battery and hybrid) are developed. Research questions on different levels from conceptual question about vehicle modularity down to detailed technological aspects like combining hydrogen storage with cabin climatisation are covered by this project. This paper shows the holistic research approach and presents a selection of vehicle concepts and technology topics.}
}
J. Mazzega, F. Köster, K. Lemmer, und T. Form, "Absicherung hochautomatisierter Fahrfunktionen" ATZ Automobiltechnische Zeitschrift, vol. 118, iss. 10.
@article{dlr107250, volume = {118},
number = {10},
month = {Oktober},
author = {Jens Mazzega and Frank K{\"o}ster and Karsten Lemmer and Thomas Form},
series = {ATZ - Automobiltechnische Zeitschrift},
title = {Absicherung hochautomatisierter Fahrfunktionen},
publisher = {Axel Springer Verlag},
year = {2016},
journal = {ATZ Automobiltechnische Zeitschrift},
keywords = {Automatisiertes Fahren PEGASUS},
url = {http://elib.dlr.de/107250/}
}
F. Köster, B. Jäger, M. M. zu Hörste, und T. Hesse, "Automatisiertes Fahren - Kann die Schiene von der Straße lernen? (ein technisch-betrieblicher Vergleich)" ZEVrail - Zeitschrift für das gesamte System Bahn, iss. 140.
@article{dlr106606, number = {140},
month = {Oktober},
author = {Frank K{\"o}ster and B{\"a}rbel J{\"a}ger and Michael Meyer zu H{\"o}rste and Tobias Hesse},
editor = {Hans-Peter Lang and Olaf Naujoks and Christian Schindler and Peter Veit},
title = {Automatisiertes Fahren - Kann die Schiene von der Stra{\ss}e lernen? (ein technisch-betrieblicher Vergleich)},
publisher = {Georg Siemens Verlag},
year = {2016},
journal = {ZEVrail - Zeitschrift f{\"u}r das gesamte System Bahn},
pages = {416--423},
keywords = {Automatisiertes Fahren, Bahn, Stra{\ss}e, Schienenverkehr, Verkehrssysteme},
url = {http://elib.dlr.de/106606/},
abstract = {Automatisierung ist eine Schl{\"u}sselfrage f{\"u}r die Erh{\"o}hung der Sicherheit und Effizienz im Stra{\ss}enverkehr und die Erh{\"o}hung der Leistungsf{\"a}higkeit und Flexibilit{\"a}t im Schienenverkehr. Beide Systeme unterscheiden sich grunds{\"a}tzlich in Spurf{\"u}hrung und Bremsweg, Art der Steuerung und des Systemdurchgriffes, dem Zusammenspiel Fahrzeug-Infrastruktur sowie der Sicherheitsphilosophie. Auf der Stra{\ss}e unterst{\"u}tzen hoch entwickelte Assistenzsysteme den Fahrer. Auf der Schiene wird schon seit den 80er Jahren im Metrobetriebe vollautomatisiert gefahren. Neue Herausforderungen ergeben sich hier f{\"u}r eine weitergehende Automatisierung auf offenen Strecken. Trotz der systembedingten Unterschiede gibt es bei beiden Verkehrssystemen auch vergleichbare Fragestellungen, deren L{\"o}sung in den einzelnen Systemen einen ganz unterschiedlichen Reifegrad aufweist. Ein jeweiliger Blick {\"u}ber den Tellerrand lohnt also. {\"U}bernehmen sollte der Sektor Bahn die geschlossene Vorgehensweise des Automotive Sektors und das Thema gleichfalls in einem Dialog mit Wirtschaft, Betreibern, zulassender Beh{\"o}rde, Forschung und Politik vorantreiben und parallel regulatorische und rechtliche Fragestellungen kl{\"a}ren.}
}
S. Knake-Langhorst, K. Gimm, T. Frankiewicz, und F. Köster, "Test Site AIM -- Toolbox and Enabler for Applied Research and Development in Traffic and Mobility" Transportation Research Procedia, vol. 14.
@article{dlr98595, volume = {14},
month = {Juni},
author = {Sascha Knake-Langhorst and Kay Gimm and Tobias Frankiewicz and Frank K{\"o}ster},
title = {Test Site AIM {--} Toolbox and Enabler for Applied Research and Development in Traffic and Mobility},
publisher = {Elsevier},
journal = {Transportation Research Procedia},
pages = {2197--2206},
year = {2016},
keywords = {intelligent mobility services; test site; situation assessment; V2X communications; cooperative systems},
url = {http://elib.dlr.de/98595/},
abstract = {The Application Platform for Intelligent Mobility (AIM) is a test site for research and development in the domain of intelligent mobility services, which resides in the city of Braunschweig and in parts of the circumjacent regions. The test site, which was set into operation in 2014, contains powerful instruments for simulating, measuring and manipulating microscopic and macroscopic aspects of traffic and mobility. Thus, AIM can serve as platform for research and development projects with high systemic and technical demands. For this purpose, AIM contains simulation environments, specific test tracks and {--} above all {--} several service platforms in the field. The manuscript gives a detailed inside view on two of the most sophisticated services: The AIM Research Intersection is an instrument for detection and assessment of traffic behavior in a complex intersection under real-time conditions. The AIM Reference Track provides V2X functionality for long-term operation in the scale of an urban environment. For both services field applications are depicted to demonstrate the opportunities for individual usage. In addition, AIM services can be seen as relevant components of a toolbox for research and development in the field of applied mobility services. That means that services can be combined to generate multiple options for further applications as additional value apart from their particular task. The manuscript exemplarily outlines a combination of the aforementioned services to bring up the opportunity of infrastructural supported cooperative driver assistance systems. The manuscript ends with a sum-up and an outlook on future works and the integration in the further development outline of AIM.}
}
F. Köster, T. Form, K. Lemmer, und J. Plättner, "Wie gut müssen - automatisierte Fahrzeuge fahren - PEGASUS" in Proc. AAET 2016 - Automatisierungssysteme, Assistenssysteme und eingebettete Systeme für Transportmittel, 2016.
@inproceedings{dlr103235, month = {Februar},
author = {Frank K{\"o}ster and Thomas Form and Karsten Lemmer and Jens Pl{\"a}ttner},
booktitle = {AAET 2016 - Automatisierungssysteme, Assistenssysteme und eingebettete Systeme f{\"u}r Transportmittel},
editor = {(Hrsg.) ITS automotive nord},
title = {Wie gut m{\"u}ssen - automatisierte Fahrzeuge fahren - PEGASUS},
journal = {Tagungsband: AAET 2016},
pages = {292--300},
year = {2016},
keywords = {PEGASUS, Automatisierte Fahrzeuge},
url = {http://elib.dlr.de/103235/},
abstract = {Das Projekt PEGASUS (Projekt zur Etablierung von generell akzeptierten G{\"u}tekriterien, Werkzeugen und Methoden sowie Szenarien und Situationen zur Freigabe hochautomatisierter Fahrfunktionen) schlie{\ss}t wesentliche L{\"u}cken im Bereich des Testens sowie zur Freigabe hochautomatisierter Fahrfunktionen. PEGASUS leistet damit einen Beitrag, dass Ergebnisse aus Forschungs- und Entwicklungsprojekten zum hochautomatisierten Fahren sowie bereits existierende Fahrzeugprototypen in marktf{\"a}hige Produkte {\"u}berf{\"u}hrt werden k{\"o}nnen. Hierzu werden im Projekt u.a. Kriterien und Ma{\ss}e zur Funktionsbewertung erarbeitet, G{\"u}teniveaus festgelegt und die f{\"u}r Tests und Freigaben ben{\"o}tigten Methoden sowie Werkzeugketten aufgebaut. Die Projektergebnisse werden praktisch angewendet und hinsichtlich ihrer Wirksamkeit und Praxistauglichkeit bewertet. Zentraler Use-Case des Projekts ist die Funktion des hochautomatisierten Autobahn-Chauffeurs. Die bislang herstellerspezifischen Vorgehensweisen zur Erprobung und Absicherung von Assistenzfunktionen bzw. Automatisierungsfunktionen werden durch PEGASUS in ein neues Vorgehen {\"u}berf{\"u}hrt, welches sich auf wissenschaftlich motivierten Kriterien, Ma{\ss}en, G{\"u}teniveaus, Testkatalogen, Testmethoden und entsprechend ausgerichteten Werkzeugketten abst{\"u}tzt. Das Projekt definiert damit erstmals einen wissenschaftlich hergeleiteten Rahmen zum Testen und zur Freigabe hochautomatisierter Fahrzeuge. Am Projekt PEGASUS sind 17 Einrichtungen aus Wirtschaft und Wissenschaft beteiligt . Das Projekt startete im Januar 2016, hat ein Projektvolumen von ca. 34,5 Mio. Euro und eine Laufzeit von 46 Monaten.}
}
S. Lapoehn, M. Dziennus, A. Schieben, F. Utesch, T. Hesse, F. Köster, M. Dotzauer, und K. Johann, Interaction design for nomadic devices in highly automated vehicles.
@misc{dlr103550, month = {September},
title = {Interaction design for nomadic devices in highly automated vehicles},
author = {Stephan Lapoehn and Marc Dziennus and Anna Schieben and Fabian Utesch and Tobias Hesse and Frank K{\"o}ster and Mandy Dotzauer and Kelsch Johann},
year = {2016},
journal = {Mensch und Computer 2016 Proceedings},
keywords = {automated driving, nomadic device, takeover, transition},
url = {http://elib.dlr.de/103550/},
abstract = {Following the roadmaps of (inter)national committees, highly automated driving will be available in the next decade in production vehicles. This technology allows the driver to do some other tasks while driving and to remain only as a fallback in situations the automation is not capable to handle. This study tested if nomadic devices, that drivers might use while driving highly automated, can be integrated to support the driver in taking over control when requested. 33 drivers participated in a simulator study and drove in a highly automated vehicle on a motorway. The results showed that the takeover performance of drivers improve if the takeover request is displayed additionally on the nomadic device. Therefore, the integration of additional interfaces such as smartphones into a holistic interaction concept may be a key aspect for designing a secure and comfortable takeover process.}
}
S. Knake-Langhorst, K. Gimm, T. Frankiewicz, und F. Köster, "Test Site AIM -- Toolbox and Enabler for Applied Research and Development in Traffic and Mobility" in Proc. Moving Forward: Innovative Solutions for Tomorrow's Mobility (6th European Transport Research Conference), 2016.
@inproceedings{dlr98594, booktitle = {Moving Forward: Innovative Solutions for Tomorrow's Mobility (6th European Transport Research Conference)},
month = {April},
title = {Test Site AIM {--} Toolbox and Enabler for Applied Research and Development in Traffic and Mobility},
author = {Sascha Knake-Langhorst and Kay Gimm and Tobias Frankiewicz and Frank K{\"o}ster},
year = {2016},
keywords = {intelligent mobility services; test site; situation assessment; V2X communications; cooperative systems},
url = {http://elib.dlr.de/98594/},
abstract = {The Application Platform for Intelligent Mobility (AIM) is a test site for research and development in the domain of intelligent mobility services, which resides in the city of Braunschweig and in parts of the circumjacent regions. The test site, which was set into operation in 2014, contains powerful instruments for simulating, measuring and manipulating microscopic and macroscopic aspects of traffic and mobility. Thus, AIM can serve as platform for research and development projects with high systemic and technical demands. For this purpose, AIM contains simulation environments, specific test tracks and {--} above all {--} several service platforms in the field. The manuscript gives a detailed inside view on two of the most sophisticated services: The AIM Research Intersection is an instrument for detection and assessment of traffic behavior in a complex intersection under real-time conditions. The AIM Reference Track provides V2X functionality for long-term operation in the scale of an urban environment. For both services field applications are depicted to demonstrate the opportunities for individual usage. In addition, AIM services can be seen as relevant components of a toolbox for research and development in the field of applied mobility services. That means that services can be combined to generate multiple options for further applications as additional value apart from their particular task. The manuscript exemplarily outlines a combination of the aforementioned services to bring up the opportunity of infrastructural supported cooperative driver assistance systems. The manuscript ends with a sum-up and an outlook on future works and the integration in the further development outline of AIM.}
}
A. Richter, M. Scholz, H. Friedl, T. Ruppert, und F. Köster, "Challenges and experiences in using heterogeneous, geo-referenced data for automatic creation of driving simulator environments" SIMULATION, vol. 92, iss. 5.
doi: 10.1177/0037549716641201
@article{doi:10.1177/0037549716641201,
author = {Andreas Richter and Michael Scholz and Hartmut Friedl and Thomas Ruppert and Frank K{\"o}ster},
title ={Challenges and experiences in using heterogeneous, geo-referenced data for automatic creation of driving simulator environments},
journal = {SIMULATION},
volume = {92},
number = {5},
pages = {437-446},
year = {2016},
doi = {10.1177/0037549716641201},
URL = { https://doi.org/10.1177/0037549716641201},
eprint = { https://doi.org/10.1177/0037549716641201},
abstract = { For the development of advanced driving assistance and automation systems the simulation plays an important role. Urban areas get increasing emphasis, especially in the context of future Car2X-communication. This article describes an approach developed in the project Virtual World. Its goal is to model such virtual three-dimensional (3D) environments and logical road descriptions automatically based on a tool chain from heterogeneous geographic datasets (e.g., cadastral data, road surveying, aerial pictures, and crowd-sourced data). As proof of concept, the urban area of Braunschweig, Germany, was chosen. The article focuses on the generation of a 3D city model with corresponding road network description suitable for driving and traffic simulations as used in research and industry. The article gives technical descriptions of the major work steps and discusses issues regarding the availability of data. It concludes with the current project outcome and further development in the project. }
}
P. P. Fouopi, G. Srinivas, S. Knake-Langhorst, und F. Köster, "Object Detection Based on Deep Learning and Context Information" in Proc. New Challenges in Neural Computation and Machine Learning, 2016.
@inproceedings{dlr112764, booktitle = {New Challenges in Neural Computation and Machine Learning},
editor = {Thomas Villmann and Frank-Michael Schleif},
title = {Object Detection Based on Deep Learning and Context Information},
author = {Paulin Pekezou Fouopi and Gurucharan Srinivas and Sascha Knake-Langhorst and Frank K{\"o}ster},
year = {2016},
journal = {Machine Learning reports},
keywords = {Object Detection, Deep Learning, Convolutional Neural Networks, Context Information, Semantic Models, Bayesian Models},
url = {http://elib.dlr.de/112764/},
abstract = {In order to avoid collision with other traffic participants automated driving vehicles need to understand the scene around the ego-vehicle. Object detection as part of scene understanding remains a challenging task due to the highly variable object appearances. Object appearances can vary according to position, occlusion, illumination, etc. In this work we propose a combination of convolutional neural networks and context information to improve object detection. Context information and deep learning architectures, which are relevant for object detection, are chosen. Different approaches for integrating context information into the convolutional neural networt are discussed. The combined classifier is trained and evaluated on real scene data.}
A. Richter, M. Fischer, T. Frankiewicz, L. Schnieder, und F. Köster, "Reducing the gap between simulated and real life environments by introducing high-precision data" in Proc. Driving Simulator Conference 2015 Europe, 2015.
@inproceedings{dlr98290, booktitle = {Driving Simulator Conference 2015 Europe},
editor = {Heinrich B{\"u}lthoff and Kemeny Andras and Prettp Paolo},
month = {September},
title = {Reducing the gap between simulated and real life environments by introducing high-precision data},
author = {Andreas Richter and Martin Fischer and Tobias Frankiewicz and Lars Schnieder and Frank K{\"o}ster},
year = {2015},
pages = {227--228},
keywords = {simulation based testing, virtual environment design, high-precision data, urban reference track},
url = {http://elib.dlr.de/98290/},
abstract = {The Institute of Transportation Systems of the German Aerospace Center recently started operating a large-scale research facility called Application Platform for Intelligent Mobility (AIM) to support the development and evaluation of Intelligent Transport Systems and mobility applications in the urban area of Braunschweig, Germany. The overarching goals are to improve safety for all traffic participants, to increase efficiency of traffic flows, and to protect resources. An important part of this new research facility is to provide a reference track on a public road surrounding the downtown, which will be equipped with ITS Roadside Stations for Vehicle-to-X (V2X) communication and additional sensors (e.g. cameras) for comprehensive data collection. Also communication to a traffic management centre and distribution of data to vulnerable road users and passengers via one of the regular WLAN standards is envisaged. One important purpose of the reference track is the development and efficient field operational test of ITS applications that use V2X communication. Before testing new applications or algorithms in a realistic environment it is necessary to evaluate them in a simulation, first. AIM will support this development step by providing a virtual counterpart to the reference track. A large part of Braunschweig is digitally represented with the help of a GIS database developed by a tool chain called SimWorld Urban. A virtual landscape (as a 3D model) and a logical road description (using the de facto standard OpenDRIVE) are automatically generated out of real world data (like cadastral plans, road measurement, aerial photographs, navigation data, etc.). By providing a higher level of reality the currently existing gap between simulation and test trial results will be significantly reduced and therefore significantly lowers the risk of conducting potentially expensive field operational tests with immature applications. The paper will explain the concept of this approach and its challenges.}
}
L. Schnieder und F. Köster, "Assistenz und Automation am Übergang zwischen individueller und kollektiver Mobilität" Internationales Verkehrswesen, vol. 67, iss. 3.
@article{dlr98106, volume = {67},
number = {3},
month = {September},
author = {Lars Schnieder and Frank K{\"o}ster},
editor = {Kay Axhausen and Hartmut Fricke and Sebastian Kummer and Barbara Lenz and Knut Ringat},
title = {Assistenz und Automation am {\"U}bergang zwischen individueller und kollektiver Mobilit{\"a}t},
publisher = {DVV Media Group GmbH},
year = {2015},
journal = {Internationales Verkehrswesen},
pages = {96--99},
keywords = {Verkehrsautomatisierung, Fahrzeugautomatisierung, Intermodalit{\"a}t, {\"O}PNV},
url = {http://elib.dlr.de/98106/},
abstract = {Vorhandene Verkehrsinfrastrukturen sto{\ss}en zunehmend an ihre Kapazit{\"a}tsgrenzen. Der Bau weiterer Verkehrsfl{\"a}chen ist meist weder r{\"a}umlich noch finanziell realisierbar. Alternative Mobilit{\"a}tsmodelle spielen folglich in Ballungsr{\"a}umen eine zunehmend gr{\"o}{\ss}ere Rolle. F{\"u}r junge Menschen ist das Konzept {"`}Nutzen statt Besitzen{"'} eine realistische Option zur Befriedigung ihrer Mobilit{\"a}tsbed{\"u}rfnisse. Die Verkn{\"u}pfung individueller und kollektiver Mobilit{\"a}tsangebote ist hierbei ein wesentliches Element. Entscheidend f{\"u}r den Erfolg solcher Angebote ist, dass die Nutzer ihre Verkehrsmittelwahl auf der Basis der vor Ort vorhandenen Mobilit{\"a}tsoptionen je nach Reisezweck und Verf{\"u}gbarkeit flexibel optimieren k{\"o}nnen.}
}
B. Schonlau, S. Grimm, F. Köster, und T. Frankiewicz, "AIM-Testfeld für kooperative Funktionen" ATZ Automobiltechnische Zeitschrift, vol. 05.
@article{dlr96540, volume = {05},
month = {Mai},
author = {Benedikt Schonlau and Stephan Grimm and Frank K{\"o}ster and Tobias Frankiewicz},
title = {AIM-Testfeld f{\"u}r kooperative Funktionen},
publisher = {Springer Vieweg},
journal = {ATZ Automobiltechnische Zeitschrift},
pages = {54--58},
year = {2015},
keywords = {Vehicle-to-X Kommunikation, V2X Car2X, kooperative Fahrerassistenzsysteme},
url = {http://elib.dlr.de/96540/},
abstract = {Fahrzeughersteller, Zulieferer und Forschungseinrichtungen entwickeln zurzeit Funktionen, die standardisierte Nachrichten zwischen Fahrzeugen und Verkehrsinfrastrukturelementen austauschen, um Unf{\"a}lle zu vermeiden oder Unfallschweren zu mindern. Die Kommunikation erfolgt {\"u}ber Wireless LAN Hardware mit einem speziell auf die Fahrzeug-Fahrzeug- und Fahrzeug-Infrastruktur-Kommunikation (V2X-Kommunikation) angepassten Kommunikationsprotokoll. Das Kommunikationsprotokoll wurde von der IEEE im Standard 802.11p weltweit einheitlich standardisiert. Die f{\"u}r die Kommunikation notwendigen Anwendungsnachrichten wurden vom Car to Car Communication Consortium f{\"u}r die europ{\"a}ische Anwendung standardisiert. M{\"o}gliche Funktionen sind zum Beispiel Warnungen vor Baustellen oder Gefahrenstellen, Ampelassistenten, die den Fahrer beim Erreichen von Lichtsignalanlagen unterst{\"u}tzen oder in einer sp{\"a}teren Generation Notbremsassistenten, die das {\"u}berfahren einer roten Ampel verhindern. Diese kooperativen Sicherheitsfunktionen stellen Anforderungen an neue Testinfrastrukturen. Um die Funktionen hinreichend testen zu k{\"o}nnen, wird eine in den flie{\ss}enden Verkehr eingebettete Testumgebung ben{\"o}tigt, wie sie das Anwendungsfeld intelligente Mobilit{\"a}t (AIM) darstellt.}
}
S. Knake-Langhorst, K. Gimm, und F. Köster, "AIM Research Intersection - Infrastructure for research on interacting urban traffic" in Proc. 27th ICTCT Workshop, 2015.
@inproceedings{dlr95265, booktitle = {27th ICTCT Workshop},
title = {AIM Research Intersection - Infrastructure for research on interacting urban traffic},
author = {Sascha Knake-Langhorst and Kay Gimm and Frank K{\"o}ster},
year = {2015},
keywords = {situation detection, intersection safety, severity of traffic conflicts at intersections, safety indicators, surrogate safety measures, safety performance indicators, collision risk assessment, threat assessment measure, crash proximity measure},
url = {http://elib.dlr.de/95265/}
}
E. Böde, H. Daembkes, W. Damm, F. Griebel, F. Köster, K. Lemmer, A. Lüdtke, J. Niehaus, und T. Peikenkamp, SafeTRANS: Safety, Testen und Entwicklungsprozesse hochautomatisierter SystemeExpert Verlag.
@incollection{dlr96889, volume = {137},
author = {Eckard B{\"o}de and Heinrich Daembkes and Werner Damm and Franziska Griebel and Frank K{\"o}ster and Karsten Lemmer and Andreas L{\"u}dtke and J{\"u}rgen Niehaus and Thomas Peikenkamp},
series = {Haus der Technik},
editor = {Werner Klaffke},
title = {SafeTRANS: Safety, Testen und Entwicklungsprozesse hochautomatisierter Systeme},
publisher = {Expert Verlag},
year = {2015},
journal = {Fahrerassistenz und Aktive Sicherheit},
pages = {184--200},
keywords = {Hochautomatisierte Systeme},
url = {http://elib.dlr.de/96889/},
abstract = {SafeTRANS ist ein gemeinn{\"u}tziger deutscher Verein, der sich insbesondere zum Ziel gesetzt hat, Prozesse, Methoden und Werkzeuge zu erforschen, die die Entwicklung sicherer Embedded Systems in der Verkehrstechnik zu verbessern. Im Januar 2015 wurde dazu ein Arbeitskreis Hochautomatisierte Systeme: Safety, Testen und Entwicklungsprozesse gegr{\"u}ndet. Hierin wollen Teilnehmer aus unterschiedlichen Bereichen der Verkehrstechnik zusammenarbeiten, um gemeinsame Ans{\"a}tze f{\"u}r die Entwicklung und den Test von hochautomatisierten sicherheitskritischen Systemen zu erarbeiten. Als ein erster gemeinsamer Arbeitspunkt wurde die Definition eines interperabelen Umweltmodels f{\"u}r die Umgebung der mobilen Plattform identifiziert. Dieses {\"U}berblickspaper stellt kurz den Verein SafeTRANS und dessen Arbeitskreis dar und gibt dann einen {\"U}berblick {\"u}ber die Resultate einschl{\"a}giger durch SafeTRANS initiierter Projekte zu Methoden der Modellierung und Absicherung der Mensch-Assistenzsystem-Interaktion und er Sicherheit von Assistenzsystemen.}
}
S. Lapoehn, A. Schieben, T. Hesse, J. Schindler, und F. Köster, "Concept of Controlling the Usage of Nomadic Devices in Highly-Automated Vehicles" IET Intelligent Transport Systems.
@article{dlr95262, title = {Concept of Controlling the Usage of Nomadic Devices in Highly-Automated Vehicles},
author = {Stephan Lapoehn and Anna Schieben and Tobias Hesse and Julian Schindler and Frank K{\"o}ster},
publisher = {IET},
year = {2015},
journal = {IET Intelligent Transport Systems},
pages = {599--605},
keywords = {nomadic device, automated driving, advanced driver assistance systems},
url = {http://elib.dlr.de/95262/},
abstract = {Today, the automobile industry and several research institutes develop automated vehicles for several driving applications. With increasing capabilities of automation the driver can be more and more dispensed from the driving task and might want to use his nomadic devices to get entertained, read the news or do office work while driving. However, in some complex driving situations (like road works, freeway exit ramps or lane closure due to car accidents) the automation still needs to safely hand over the control to the driver. These situations require a lot of attention by the driver who must not be tempted to ignore the warnings of the assistance system and to continue any task on the nomadic device until a critical situation originates. This paper describes a method to link nomadic devices to vehicles to support a safe usage during highly automated driving and a first approach to ensure a safe transition between different automation modes. Therefore, the automation system is connected to the nomadic device in the vehicle and has the ability to actively control the content on the screen. The proof of concept is demonstrated in a research vehicle that drives on a simulated motorway.}
}
T. Frankiewicz, F. Köster, S. Grimm, D. Hermann, und B. Schonlau, "Nutzung des Testfeldes AIM für die Absicherung von kooperativen Sicherheitsfunktionen" in Proc. AAET - Automatisierungssysteme, Assistenzsysteme und eingebettete Systeme für Transportmittel, 2015.
@inproceedings{dlr94479, booktitle = {AAET - Automatisierungssysteme, Assistenzsysteme und eingebettete Systeme f{\"u}r Transportmittel},
month = {Februar},
title = {Nutzung des Testfeldes AIM f{\"u}r die Absicherung von kooperativen Sicherheitsfunktionen},
author = {Tobias Frankiewicz and Frank K{\"o}ster and Stephan Grimm and Daniel Hermann and Benedikt Schonlau},
year = {2015},
pages = {192--207},
keywords = {Testfeld AIM, V2X Kommunikation, Car2Car, Car2X, Car2I, Feldtest, Field Operational Test},
url = {http://elib.dlr.de/94479/},
abstract = {Im Rahmen der Standardisierungsaktivit{\"a}ten des Car2Car Communication Consortium arbeiten derzeit verschiedene OEM, Zulieferer und wissenschaftliche Institute an der Weiterentwicklung von V2X-Funktionen (Vehicle-to-Vehicle bzw. Vehicle-to-Infrastructure-Funktionen), wie zum Beispiel Warnung vor Einsatzfahrzeugen, Warnung vor Baustellensperranh{\"a}ngern oder Gr{\"u}nlichtbevorrechtigungen an Lichtsignalanlagen. Die Herausforderung beim Testen solcher V2X-Funktionen liegt in der Komplexit{\"a}t des Systems und der Anzahl der beteiligten Komponenten sowohl im Fahrzeug als auch in der Infrastruktur. So sind beispielsweise Sende- oder Empfangskomponenten unterschiedlicher Hersteller und Standards im Einsatz. Dar{\"u}ber hinaus sind {\"u}blicherweise auf der Infrastrukturseite sehr heterogene Architekturen und Backendstrukturen installiert, sodass einer Vereinheitlichung und Standardisierung der Testkomponenten eine sehr hohe Bedeutung zukommt, um die Systeme skalierbar zu entwickeln. Eine Erprobung und Absicherung dieser Funktionen erfordert sehr hohen Aufwand, da es nicht mehr ausreicht, die Fahrzeuge einzeln zu testen, sondern das Zusammenspiel mehrerer Fahrzeuge und der beteiligten Infrastruktur getestet werden muss. Die zus{\"a}tzliche Herausforderung besteht darin, dass die Funktionen auch hersteller{\"u}bergreifend funktionieren m{\"u}ssen und in der Standardisierung nur der sendeseitige Funktionsumfang beschrieben ist. Eine M{\"o}glichkeit zur Reduzierung des Aufwandes liegt in der Nutzung des Testfeldes Anwendungsplattform Intelligente Mobilit{\"a}t (AIM) in Braunschweig, welches vom DLR betrieben wird. Im Testfeld AIM wird die real vorhandene Infrastruktur, z.B. Lichtsignalanlagen (LSA) und Road Side Units (RSU) genutzt, um beispielsweise zu testen, ob die Sende- und Empfangsseite des Lichtsignalphasenassistenten fehlerfrei funktioniert. Es k{\"o}nnen weiterhin reale Sende- und Empfangsfahrzeuge im Testfeld bewegt werden und {\"u}ber die im Testfeld befindlichen RSUs k{\"o}nnen die Nachrichten, welche zwischen den Fahrzeugen verschickt werden, unabh{\"a}ngig aufgezeichnet und danach ausgewertet werden. Durch die Nutzung des Testfeldes AIM und dessen Prozesse l{\"a}sst sich der Testaufwand verringern sowie die Testtiefe erh{\"o}hen, da zus{\"a}tzlich zu den zu testenden fahrzeugseitigen V2X-Funktionen auch eine infrastrukturseitige Prozessierung und Bewertung der Daten stattfindet. Die hier eingesetzten infrastrukturseitigen Komponenten des kooperativen Testfeldes AIM bestehen im Wesentlichen aus drei Modulen: 1.) Der V2X Referenzstrecke, einer Anordnung von 35 RSUs auf dem inneren Ring der Stadt Braunschweig, mit denen internationale Standards der V2X Kommunikation sowie eigene Protokolle entwickelt und getestet werden k{\"o}nnen 2.) Einer Applikationsschicht auf den RSUs, die eine lokale Datenaufbereitung der lokal zur Verf{\"u}gung stehenden Daten betreibt und aus der infrastrukturseitige Anteile der kooperativen Assistenz bedient werden 3.) Einer {\"u}bergeordneten Schicht, in der in quasi-Echtzeit fahrzeug- und infrastrukturseitige Daten prozessiert werden und die zur Entwicklung und Test von lokalen und zentralen Services dient und auf der Prozesse zur Datenerhebung und Qualit{\"a}tssicherung laufen. Im vorliegenden Artikel werden die Architektur und Prozesslandschaft der drei Module und deren Zusammenspiel im Rahmen der Entwicklung der kooperativen Assistenz erl{\"a}utert. Neben der Datenaufbereitung f{\"u}r die fahrzeugseitige Assistenz wird dabei auch das Verfahren erl{\"a}utert, mit dem im Testfeld AIM in Braunschweig teilautomatisiert V2X Qualit{\"a}tsdaten zur technischen Validierung der Strecke erhoben werden.}
}
S. Knake-Langhorst, K. Gimm, und F. Köster, "AIM Forschungskreuzung - Baustein für den Aufbau von kooperativer Fahrerassistenz und Automation" in Proc. 16. Symposium Automatisierungssysteme, Assistenzsysteme und eingebettete Systeme für Transportmittel (AAET), 2015.
@inproceedings{dlr95264, booktitle = {16. Symposium Automatisierungssysteme, Assistenzsysteme und eingebettete Systeme f{\"u}r Transportmittel (AAET)},
title = {AIM Forschungskreuzung - Baustein f{\"u}r den Aufbau von kooperativer Fahrerassistenz und Automation},
author = {Sascha Knake-Langhorst and Kay Gimm and Frank K{\"o}ster},
year = {2015},
pages = {117--136},
keywords = {Situationserfassung, kritische Verkehrssituationen, Metriken},
url = {http://elib.dlr.de/95264/}
}
K. Ihme, F. Köster, und M. Jipp, "Experimentelle Untersuchungen zur Messung von Emotionen im Verkehr" in Proc. DLR Next Generation Forum 2015, 2015.
@inproceedings{dlr100957, booktitle = {DLR Next Generation Forum 2015},
month = {Dezember},
title = {Experimentelle Untersuchungen zur Messung von Emotionen im Verkehr},
author = {Klas Ihme and Frank K{\"o}ster and Meike Jipp},
year = {2015},
journal = {Tagungsband Next Generation Forum 2015},
keywords = {Emotion, Emotionserkennung, Nutzerzustand, Physiologie},
url = {http://elib.dlr.de/100957/}
}
J. Kelsch, M. Dziennus, und F. Köster, "Cooperative Lane Change Assistant: Background, Implementation \& Evaluation." in Proc. AAET 2015, 2015.
@inproceedings{dlr95232, month = {Februar},
author = {Johann Kelsch and Marc Dziennus and Frank K{\"o}ster},
booktitle = {AAET 2015},
title = {Cooperative Lane Change Assistant: Background, Implementation \& Evaluation.},
journal = {AAET 2015},
pages = {65--85},
year = {2015},
keywords = {cooperation, HMI, lane change assist},
url = {http://elib.dlr.de/95232/},
abstract = {Drivers can cooperate with automation inside the vehicle as well as with traffic participants and intelligent infrastructure outside the vehicle. For that matter cooperation can be a successful concept for designing driver-automation or rather highly automated traffic systems. EU-Project D3CoS was aiming at related knowledge to develop a cross domain framework for design of cooperative systems. For the automotive domain this knowledge was applied to develop a Cooperative Lane Change Assistant (C-LCA) that supports drivers in dense traffic situations while performing lane changes. In this contribution theoretical background, used methods, implementation of the C-LCA, results of its evaluation and lessons learned are described.}