Ensuring Trustworthiness of AI-Enhanced Embedded Systems
In the white paper “Ensuring Trustworthiness of AI-Enhanced Embedded Systems”, Infineon Technologies and Fraunhofer IKS present how to apply a unified safety lifecycle on an AI-Based Motor Control Unit (AI-MC) illustrative use case.
For the fifth time, Fraunhofer IKS will host the international Safetronic conference in 2025. The event will take place on November 12 and 13, 2025. Register now!
Fraunhofer IKS is getting a new institute building at the Fraunhofer campus in Garching near Munich. The groundbreaking ceremony with Bavaria's Minister President Dr. Markus Söder and Economics Minister Hubert Aiwanger in October marked the official start of construction. On our new building page you will find all information about the construction progress in German.
Do you want to make your AI systems compliant with the EU regulations? Then join our training on the EU AI Act and high-risk AI systems. For more information on the content and the program, click here:
On December 11, 2025, SICK invites you to the fourth Beyond Safety Forum. The event is being held in cooperation with Fraunhofer IKS. This edition focuses on a key question: How can we ensure safety while systems become increasingly complex?
Safety and flexibility in production – a contradiction? Not at all. We will show you how you can have both and achieve higher profits. Artificial intelligence plays a decisive role in this. We will demonstrate this on February 5, 2026, at our Safe Intelligence Day with a focus on automation at Fraunhofer IKS in Munich.
The safety of a product, i.e., not causing harm, is a crucial property for its persistent success on the market and avoidance of legal risks for the manufacturer. However, since perfectsafety is typically not achievable, the question what defines acceptable safety and what defines acceptable risks, i.e., risk acceptance criteria (RAC), arises.
Consultation projects play a crucial role in fulfilling the Fraunhofer mission of translating cutting-edge research into industry applications. Recently, Fraunhofer IKS cooperated with the South Korean company ZIOVISION on AI-based facial fracture segmentation from medical images. The successful outcome of the project demonstrates the potential benefits such collaborations offer to both partners.
“Standards are key to understand each other in an extended eco system”
Delphine Kervarec-Vicq, Product Safety Director at Valeo, is a new member of the program committee for Safetronic, the international conference on holistic safety for road vehicles. In an interview with Safe Intelligence online magazine, she talks about her motivation for joining the committee and explains the importance of safety for automated driving.
Without safety, new mobility solutions will fall to the wayside
Not only management consultancies, but also other strategic players see the increasing importance of Remote Driving Systems (RDS) for the transportation of the future. But is the concept safe enough? An extensive two-year operation without safety drivers has confirmed the technical feasibility and safety of RDS. And not only that: a comprehensive training framework for Remote Drivers has demonstrably improved performance and safety.
“Bringing the best technology safely into the vehicle”
Ensuring the safety of AI functions in vehicles remains a challenge that must be mastered step by step. However, visible progress is being made on the road to autonomous driving, says Dr. Reinhard Stolle, deputy director of the Fraunhofer IKS. And the success of ChatGPT & Co. is also likely to be leveraged for highly automated vehicles.
Safe.trAIn: AI as train conductor on regional railways
Autonomous driving is not only set to conquer the roads, but also offers enormous potential for driverless trains in rail transport. Proof of this is the safe.trAIn project, in which Fraunhofer IKS has taken on the central task of methodically assuring the AI functions.
Metrics as an indicator of AI safety: is that enough?
The performance of machine learning (ML) models is typically assessed using metrics such as accuracy, precision, recall, F1 score, etc. But how trustworthy are these single point estimates really? Such metrics reflect reality only partially and can provide us with a false sense of safety. Especially in safety-critical areas, this can be dangerous. Fraunhofer IKS develops a formal framework for the quantification of uncertainty which aims to make the residual risk “more computable”.
Would you like to know more about the research of Fraunhofer IKS? Then take a look at our Safe Intelligence online magazine. Here you can find out more about our research projects and our employees.
Would you like to know who your potential colleagues at Fraunhofer IKS are? Read our employee portraits on our Safe Intelligence Blog to find out what motivates our colleagues and what they are working on!
Fraunhofer Institute for Cognitive Systems IKS