Safety engineering support through generative AI and large language models

The Fraunhofer IKS Safety Assistant is an innovative front-end solution designed to support safety engineering tasks through the power of Generative AI (GenAI). As software development for safety-critical systems grows increasingly complex, our AI-based assistant offers the essential support needed to navigate these challenges effectively.

In today's fast-paced landscape, artificial intelligence is driving exponential growth across numerous industries. However, as companies seek to harness the economic potential of AI, significant safety concerns arise, particularly in safety-critical environments where automation must align with stringent safety requirements. This is especially true in manufacturing, where the rapid advancement of technologies like large language models (LLMs) and conversational AI introduces complexity that often outpaces existing safety standards.

Historically, safety innovations have lagged behind technological advancements. While this gap was manageable in the past, the accelerating pace of innovation is widening the divide between technological progress and safety assurance. Safety engineers are increasingly challenged to either slow down innovation or accept heightened risks—neither of which is a sustainable solution. This is where the Fraunhofer IKS Safety Assistant comes into play.

Our approach aims to bridge the gap between innovation and safety by empowering safety engineers with generative AI capabilities. By automating key aspects of the safety engineering workflow, such as Hazard and Risk Analysis (HARA) and the derivation of safety requirements, our assistant enables engineers to generate robust safety verifications for even the most complex applications.

Transform the way you approach safety engineering with the Fraunhofer IKS Safety Assistant—where cutting-edge technology meets rigorous safety standards.

Insight Background

Our mission is to deepen the understanding of complex relationships within safety-critical systems. The Safety Assistance approach explores how generative AI can streamline the planning of measure validation and ensure the accurate implementation of requirements.

At Fraunhofer IKS, we are at the forefront of research in trustworthy artificial intelligence, safety assurance, and resilient software systems. One of the key outcomes of this research is the development of AI safety assistants and FrontEnd-visions, which we aim to further refine and expand.

Additionally, we seek to empower engineers in the creation of robot behavior based on generated safety requirements, enabling the direct generation of control programs that adhere to all safety standards. This innovative approach ensures the seamless and safe integration of automation solutions in critical environments.

In depth information

• A safety assistant based on generative AI
• We combine the strengths of GPT with those of established safety tools - Interview