Publications

Cyber-physical systems such as autonomous vehicles must function safely and be self-adaptive and predictive to do so. In her paper, Marta Grobelna sketches how reachability analysis in combination with game theory can be used to predict risk of hazardous situations.

Co-working of automated systems and humans must be safe. Fraunhofer IKS therefore proposes an architecture that uses infrastructure sensors to prevent human-robot collisions at blind corners with respect to automated forklifts. We use a warehouse simulation to verify our approach and to estimate the impact on an automated forklift’s performance.

In their poster and their poster paper Tom Haider and his colleagues present a Markov Decision Process (MDP) to formalize changes in the environment. This allows End-to-End Deep Reinforcement Learning systems to better deal with situations they have not been trained to deal with.

As part of the ADA Lovelace Center for Analytics, Data and Applications,  Fraunhofer IKS has developed a technical white paper on machine learning methods for reliable perception of autonomous systems. It reviews, develops and evaluates new methods for quantifying uncertainty in deep neural networks.

In collaboration with Magazino GmbH, Frauhofer IKS presents a white paper on the obstacles and potentials of “DevOps for developing cyber-physical systems”:

• What is the difference between DevOps and traditional software development?
• What are the challenges in the DevOps process for cyber-physical systems?
• How can DevOps processes be implemented?

Within the white paper, scientists of Fraunhofer IKS discuss the main challenges of dependable cloud-based cyber-physical systems(-of-systems). The aim is to design them to simultaneously provide resilience, intelligence and flexibility, for which we introduce the new term »flexilience«.