Dr. rer. nat.

Weiß, Gereon

Filters

1
3
Reset filters

Settings
Now showing 1 - 3 of 3
No Thumbnail Available
Publication

DevOps for Developing Cyber-Physical Systems

2021 , Kreutz, Andreas , Weiß, Gereon , Rothe, Johannes , Tenorth, Moritz , Friedmann, Miriam

In the age of digitalization, the success or failure of a product depends on bug-free and feature-rich software. Driven by consumer expectations and competition between vendors, software can no longer be delivered as-is but needs to be continuously supported and updated for a period of time. In large and complex projects, this can be a challenging task, which many IT companies are approaching with the state-of-the-art software development process DevOps. For companies manufacturing high-tech products, software is also becoming ever more critical, and companies are struggling with handling the complexity of long-term software support. The adoption of modern development processes such as DevOps is challenging, as the real-world environment in which the systems operate induces challenges and requirements that are unique to each product and company. Once they are addressed, however, DevOps has the potential to deliver more sophisticated products with minimal software errors, thus increasing the value provided to customers and giving the company a considerable competitive advantage.

View
No Thumbnail Available
Publication

Machine Learning Methods for Enhanced Reliable Perception of Autonomous Systems

2021 , Henne, Maximilian , Gansloser, Jens , Schwaiger, Adrian , Weiß, Gereon

In our modern life, automated systems are already omnipresent. The latest advances in machine learning (ML) help with increasing automation and the fast-paced progression towards autonomous systems. However, as such methods are not inherently trustworthy and are being introduced into safety-critical systems, additional means are needed. In autonomous driving, for example, we can derive the main challenges when introducing ML in the form of deep neural networks (DNNs) for vehicle perception. DNNs are overconfident in their predictions and assume high confidence scores in the wrong situations. To counteract this, we have introduced several techniques to estimate the uncertainty of the results of DNNs. In addition, we present what are known as out-of-distribution detection methods that identify unknown concepts that have not been learned beforehand, thus helping to avoid making wrong decisions. For the task of reliably detecting objects in 2D and 3D, we will outline further methods. To apply ML in the perception pipeline of autonomous systems, we propose using the supplementary information from these methods for more reliable decision-making. Our evaluations with respect to safety-related metrics show the potential of this approach. Moreover, we have applied these enhanced ML methods and newly developed ones to the autonomous driving use case. In variable environmental conditions, such as road scenarios, light, or weather, we have been able to enhance the reliability of perception in automated driving systems. Our ongoing and future research is on further evaluating and improving the trustworthiness of ML methods to use them safely and to a high level of performance in various types of autonomous systems, ranging from vehicles to autonomous mobile robots, to medical devices.

View
No Thumbnail Available
Publication

Reducing the verification effort for interfaces of automotive infotainment software

2015 , Drabek, Christian , Paulic, Annette , Weiß, Gereon

We present a novel approach and effective tooling to reduce the effort for the interface verification of in-vehicle software components. Our models create different views of the system. Layered reference models separate the description of the structure and the behavior of the services' communication. This simplifies the behavior descriptions and facilitates the usage of different communication technologies, e.g., D-Bus or CAN. Since the reference models are executable specifications, they can be used to verify the communication of the modeled services. This can be tested live or from a trace. In case of required changes to an interface, regression testing can be performed automatically using only the model. We evaluate the benefits and implications of our approach and tool with a case study of an in-vehicle audio function.

View