Dr. rer. nat.

Weiß, Gereon

Filters

1 1
Reset filters

Settings
Now showing 1 - 10 of 56
No Thumbnail Available
Publication

Automatic Deduction of the Impact of Context Variability on System Safety Goals

2024 , Kreutz, Andreas , Weiß, Gereon , Trapp, Mario

Autonomous systems, such as trains with a high grade of automation, need to function safely in their operational context. One hindrance to the development of such systems is the high degree of variability of this context: Different context variants can have a substantial impact on the safety goals the system must fulfill to function with sufficiently low residual risk.In this paper, we propose a method for modeling and reasoning about the context variability of an autonomous system and its impact on the system’s safety. We build upon contextual goal models to model the refinement of safety goals and their dependence on the environment. By introducing an explicit model of the context variability to be expected, we transform the challenge of safety in variable environments to a satisfaction modulo theories problem. This allows us to find inconsistencies and check whether a concrete context variant would allow for safe operation of the system. We demonstrate our approach with a use case from the railway domain and show its applicability to an automatic train operation system in different contexts based on map data.

View
No Thumbnail Available
Publication

Adaptively Managing Reliability of Machine Learning Perception under Changing Operating Conditions

2023 , Salvi, Aniket , Weiß, Gereon , Trapp, Mario

Autonomous systems are deployed in various contexts, which makes the role of the surrounding environment and operational context increasingly vital, e.g., for autonomous driving. To account for these changing operating conditions, an autonomous system must adapt its behavior to maintain safe operation and a high level of autonomy. Machine Learning (ML) components are generally being introduced for perceiving an autonomous system’s environment, but their reliability strongly depends on the actual operating conditions, which are hard to predict. Therefore, we propose a novel approach to learn the influence of the prevalent operating conditions and use this knowledge to optimize reliability of the perception through self adaptation. Our proposed approach is evaluated in a perception case study for autonomous driving. We demonstrate that our approach is able to improve perception under varying operating conditions, in contrast to the state-of-the-art. Besides the advantage of interpretability, our results show the superior reliability of ML-based perception.

View
No Thumbnail Available
Publication

Safety Implications of Runtime Adaptation to Changing Operating Conditions

2022 , Salvi, Aniket , Weiß, Gereon , Trapp, Mario , Oboril, Fabian , Buerkle, Cornelius

With further advancements of autonomous driving, also larger application scenarios will be addressed, so-called Operational Design Domains (ODDs). Autonomous vehicles will likely experience varying operating conditions in such broader ODDs. The implications of changing operating conditions on safety and required adaptation is, however, an open challenge. In our work, we exemplary investigate a vehicle following scenario passing through altering operating conditions and Responsibility Sensitive Safety (RSS) as formal model to define appropriate longitudinal following distances. We provide a deeper analysis of the influence of switching the safety model parameter values to adapt to new operating conditions. As our findings show that hard switches of operating conditions can lead to critical situations, we propose an approach for continuously adapting safety model parameters allowing for a safe and more comfortable transition. In our evaluation, we utilize driving simulations to compare the hard switching of parameters with our proposal of gradual adaptation. Our results highlight the implications of changing operating conditions on the driving safety. Moreover, we provide a solution to adapt the safety model parameters of an autonomous vehicle in such a way that safety model violations during transition can be avoided.

View
No Thumbnail Available
Publication

Implementing a Metadata Manager for Machine Learning with the Asset Administration Shell

2022 , Sawczuk da Silva, Alexandre , Van, Hoai My , Weiß, Gereon

With the rise of Industry 4.0, businesses are increasingly turning to Machine Learning to leverage data for improving quality and productivity. However, one open challenge when embracing Machine Learning in this context is the integration of cloud infrastructures, as well as the heterogeneity of data, interfaces, and protocols in the production environment. To address this, we are developing a framework that aims to simplify the adoption of Machine Learning techniques for heterogeneous industrial automation systems. One of the core features of this framework is the ability to handle data about production devices -- a scenario that is naturally suited to the use of Asset Administration Shells. However, the implementation of a system that uses Asset Administration Shells comes with its own set of challenges, such as the abstraction of details from users and the representation of device topologies. Thus, this paper introduces the concepts and implementation of a Metadata Manager component in the aforementioned framework that uses Asset Administration Shells as its basis. We further examine the Metadata Manager's current structure with unit testing, derive planned extensions, and discuss future directions from the Industry 4.0 perspective.

View
No Thumbnail Available
Publication

Approach for Argumenting Safety on Basis of an Operational Design Domain

2024 , Weiß, Gereon , Zeller, Marc , Schoenhaar, Hannes , Drabek, Christian , Kreutz, Andreas

The Operational Design Domain (ODD) is a representative model of the real world in which an Automated Driving System (ADS) is intended to operate. The definition of the ODD is a crucial part of the development process for such an artificial intelligence (AI)-enabled system. This is due to the fact that the ODD is the basis for several critical development activities, like defining system-level requirements, test & verification, and building a well-founded safety case for an AI-based ADS. Since an inadequately defined ODD poses a major safety concern for the entire development, an ODD must be defined completely and consistently during the development process. In this work, we present an approach for the ODD definition and maintenance during the development of safety-critical AI-based ADS functionalities and provide evidences to argue the sufficient completeness and consistency. We demonstrate the feasibility of our approach by an industrial use case of a fully automated system in the railway domain.

View
No Thumbnail Available
Publication

Fuzzy Interpretation of Operational Design Domains in Autonomous Driving

2022-07 , Salvi, Aniket , Weiß, Gereon , Trapp, Mario , Oboril, Fabian , Buerkle, Cornelius

The evolution towards autonomous driving involves operating safely in open-world environments. For this, autonomous vehicles and their Autonomous Driving System (ADS) are designed and tested for specific, so-called Operational Design Domains (ODDs). When moving from prototypes to real-world mobility solutions, autonomous vehicles, however, will face changing scenarios and operational conditions that they must handle safely. Within this work, we propose a fuzzy based approach to consider changing operational conditions of autonomous driving based on smaller ODD fragments, called μODDs. By this, an ADS is enabled to smoothly adapt its driving behavior for meeting safety during shifting operational conditions. We evaluate our solution in simulated vehicle following scenarios passing through different μODDs, modeled by weather changes. The results show that our approach is capable of considering operational domain changes without endangering safety and allowing improved utility optimization.

View
No Thumbnail Available
Publication

Framework for Data and AI Lifecycle. Research Project REMORA

2022 , Van, Hoai My , Dreiser, Marc , Sawczuk da Silva, Alexandre , Weiß, Gereon

There is a lot of potential for Artificial Intelligence (AI) in the industrial domain to improve services and production. The Fraunhofer IKS is developing a framework for the data and AI life cycle to support every life cycle stage from AI development through data processing to data analysis. It aims at meeting the challenges of deploying AI in the industrial domain in order to enable continuous, automated, and dynamic AI applications.

View
No Thumbnail Available
Publication

Self-Adaptive Service Deployment for Resilience of Smart Manufacturing Architectures

2023 , Van, Hoai My , Sawczuk da Silva, Alexandre , Knissel, Tim , Weiß, Gereon

Recent advances in the manufacturing sector - including edge-to-cloud continuum, machine learning, and digitalization - can enable smart manufacturing solutions, such as control optimization and predictive maintenance. One challenge in new system architectures is the efficient resource management under changing conditions while meeting process requirements, such as latency, when deploying software services. To address this, we propose an approach for self-adaptive service deployment that increases the resilience of smart manufacturing systems. We combine self-adaptation principles with run-time models - that describe the system in the form of the standardized Asset Administration Shell - to enable flexible software architectures for manufacturing. The proposed solution comprises the continuous adaptation of the service deployment in response to system changes, such as resource exhaustion or failure, to ensure an optimized operation. An evaluation of an example manufacturing use case shows that the proposed solution leads to lower execution latency and continuation of production in situations with low resources, e.g., through failures, compared to less flexible deployment approaches.

View
No Thumbnail Available
Publication

Concept for Safe Interaction of Driverless Industrial Trucks and Humans in Shared Areas

2022-06-17 , Drabek, Christian , Kosmalska, Anna , Weiß, Gereon , Ishigooka, Tasuku , Otsuka, Satoshi , Mizuochi, Mariko

Humans still need to access the same area as automated systems, like in warehouses, if full automation is not feasible or economical. In such shared areas, critical interactions are inevitable. The automation of vehicles is usually tied to an argument on improved safety. However, current standards still rely also on the awareness of humans to avoid collisions. Along with this, modern intelligent warehouses are equipped with additional sensors that can help to automate safety. Blind corners, where the view is obscured, are particularly critical and, moreover, their location can change when goods are moved. Therefor, we generalize a concept for safe interactions at known blind corners to movements in the entire warehouse. We propose an architecture that uses infrastructure sensors to prevent human-robot collisions with respect to automated forklifts as instances of driverless industrial trucks. This includes a safety critical function using wireless communication, which sporadically might be unavailable or disturbed. Therefore, the proposed architecture is able to mitigate these faults and gracefully degrades the system’s performance if required. Within our extensive evaluation, we simulate varying warehouse settings to verify our approach and to estimate the impact on an automated forklift’s performance.

View
No Thumbnail Available
Publication

Enabling Cognitive Manufacturing in Heterogeneous Industrial Automation Systems

2022 , Van, Hoai My , Dreiser, Marc , Sawczuk da Silva, Alexandre , Weiß, Gereon

With the increased digitization in the manufacturing sector, cognitive computing entails great potential to improve services and production. This is also referred to as cognitive manufacturing. The general idea is to simulate human cognitive processes - with the aim to improve decision making - by using machine learning (ML) to leverage the increased amount of data. However, the seamless adoption of cognitive computing and ML techniques to industrial automation systems on all abstraction levels is currently impeded by different challenges. Prominent blocking points are the heterogeneity of the systems, which impedes uniform data access and ML integration, and the lack of support for managing various ML life cycle phases. In this work, we propose a framework to manage data and ML life cycles in industrial automation systems. The framework comprises an architecture for the flexible integration of ML components (from component to cloud level) and their adaptive management (including retraining and updates). We address three phases of ML explicitly: pre-deployment, deployment, and post-deployment. We present first results and experiences of applying the framework to an industrial use case and discuss its future potential towards enabling cognitive manufacturing.

View