Modern AI models have demonstrated remarkable capabilities on various computer vision tasks such as image classification. Their decision-making process, though, remains mostly opaque (black box problem). This can be particularly problematic for safety-critical applications like medical imaging or autonomous driving. Fraunhofer IKS explores ways to increase the transparency of this black box.

Achieving safety with AI systems requires a comprehensive and collaborative approach, including technical, ethical, and regulatory considerations. A central aspect is designing AI systems that comply with safety requirements defined in constraints.

Digital twins are designed with the goal to create precise replicas of our physical world, but how exactly are they being used? For example, in medicine, vehicle construction and industrial production? Read on to find out.

The safetronic® is the industry's premier conference for the holistic safety of road vehicles. In November 2022, experts from the automotive industry met again to discuss challenges, solutions and trends. Although the safety of automated vehicles and, in particular, the associated safety assurance of AI are currently in the public spotlight, the experts at the conference had a different perspective. For them, a well-known topic is experiencing a revival and is emerging as a new trend topic: model-based system safety engineering (MBSE). Having worked on model-based safety engineering for well over a decade now, I'm personally as intrigued by this trend as I am skeptical about whether it's going to take off this time. That's reason enough for me to take a closer look at this potential trend from my individual perspective in this article.

In our previous article, we introduced some standardized terminology related to Autonomous Driving and Operational Design Domain (ODD). In this article, we look at the safety implications of transitioning through multiple ODDs while executing the Dynamic Driving Task (DDT).

Two leading experts from the Fraunhofer IKS and the University of York in the safety of complex systems have published a paper proposing a new approach to assure the safety of cognitive cyber-physical systems (CPS), including automated driving systems.

The standardized architecture of the Fraunhofer IKS integrates any automated driving function into an existing automated verhicle.

Safety is a property of a system and its environment. That's why predicting a system's context is so important to safety engineers. However, we must acknowledge that it is impossible to sufficiently predict and specify a system's context when it must operate outside of a controlled environment. In the previous parts of this series, we've seen how we can use self-adaptivity to build systems for uncertain, dynamic contexts. In this fourth and final part, we add the missing ingredient by taking safety engineering to the next level.

Where humans get stuck, artificial intelligence can help: for example, in the treatment of patients suffering from coronary artery disease (CAD).

What are the basic principles of self-adaptive systems? This is the basic prerequisite for bringing the concept of resilience to life. Part 3 of our series.