Fraunhofer Institute for Cognitive Systems IKS

Philipp Schleiß

Research Scientist at Fraunhofer IKS

Philipp Schleiß is Research Scientist at the Fraunhofer Institute for Cognitive Systems IKS. After successfully completing his master's degree in business informatics at the Technical University of Munich, he has been involved in various research and industry projects at Fraunhofer IKS since 2013. His main focus is on researching methods for safeguarding complex systems subject to uncertainty and ensuring real-time properties.

Can uncertainties in the perception of the environment be quantified?

Autonomous driving is based on reliable environment recognition. If errors occur here, life-threatening situations can quickly arise. This must be prevented, but a residual risk remains. Only when this can be precisely determined does it become calculable and a decision can be made as to whether or not to take it.

Perception (German)

Publications

Philipp Schleiß is the author of numerous scientific publications. You can find an overview here:

Overview at Fraunhofer Publica
Overview at Google Scholar
Towards the Quantitative Verification of Deep Learning for Safe Perception
Towards Continuous Safety Assurance for Autonomous Systems

Safety Engineering

Philipp Schleiß conducts research on the increasingly complex electronics in the automotive and industrial sectors. Safety engineering ensures and improves the safety of systems.

Safety Engineering

Memberships

AUTOSAR – Working group of Safety (WG-SAF) and »Application Interfaces (AIF)«

Projects of Philipp Schleiß

On our homepage you will find numerous projects of our colleagues around the research topics of Fraunhofer IKS. Here are the projects by Philipp Schleiß:

safe.trAIn: Safe AI for driverless trains

In the safe.trAIn project, 17 partners are working to establish the groundwork for using AI safely in driverless rail vehicles to make regional rail transport more efficient and sustainable. Fraunhofer IKS is focusing in particular on the proof of safety for AI functions, the robustness of AI and the Operational design domain (ODD).

safe.trAIn

AI assurance: Safe artificial intelligence for autonomous driving

The “KI-Absicherung” project for AI assurance, an initiative by the German Association of the Automotive Industry (VDA), has defined its goal of making the safety of in-car AI systems verifiable. To this end, the project partners are developing a stringent, verifiable chain of arguments for the assurance of AI functions in highly automated vehicles.

AI assurance

System Health Monitoring for Autonomous Systems

As part of the collaboration with the worldwide development partnership AUTomotive Open System ARchitecture (AUTOSAR) Fraunhofer IKS together with other members conducts research mainly in the practical application of System Health Management.

System Health Monitoring

Safe Adaptive Software for Fully Electric Vehicles

Within the EU-funded project SafeAdapt, a consortium of 9 partners from six European countries is making innovative changes to the E/E architecture, which will reduce the complexity of the system and raise the cost and energy efficiency.

safeAdapt

More information

On the following pages, you will learn more about the work and offerings of Fraunhofer IKS:

Safety Assurance

Safety assurance is the process of comprehensively proving the safety of a system. The first question to ask is: when is a system or artificial intelligence safe enough? What requirements must the system fulfil and how can the fulfilment of these requirements be proven? This is what Fraunhofer IKS is researching. We are also working on safety cases to prove the safety of the overall system.

Safety Assurance

Fault-tolerant Embedded Platforms

Fraunhofer IKS develops fault-tolerant embedded systems. This is because software architectures, for example for autonomous vehicles or in production plants, must not simply switch off, but must continue to function. Embedded systems and the important functions they contain must therefore always work reliably.

Embedded Systems

Safety Architectures for AI Systems

Fraunhofer IKS offers a comprehensive safety architecture for artificial intelligence. The goal is to ensure the safety of a system at all times despite expected or unexpected events. This means that a system can always switch to a safe state without having to stop or shut down. To this end, Fraunhofer IKS is working on methods for the automated safeguarding of artificial intelligence (AI) and autonomous systems.

Safety architectures