In the European research project SESAME, Fraunhofer IESE and its project partners are conducting research on a methodology for the model-based development and safety and security assurance of multi-robot systems (MRS) with Machine Learning and Deep Learning components.
Last modified:
Multi-robot systems (MRS) consist of distributed and interconnected teams of robots that can perform tasks beyond the competence of a single robot. Although MRS offer improved scalability and performance as well as increased robustness and mission capability, the lack of a systematic engineering methodology that covers the entire engineering lifecycle and efficiently addresses the salient features of MRS such as openness, uncertainty, variability, and the interdependency of safety and security leads to solutions that fail due to fragile design and unrealistic assumptions. SESAME addresses these problems through an open, modular, model-based approach to the systematic engineering of dependable MRS. To achieve this ambitious goal, SESAME combines five use cases led by end-users (in the areas of healthcare, agile manufacturing, agri-food, and inspection and maintenance) with the R&D expertise of partners with a long track record of conducting cutting-edge research in robotics, model-based safety and security, safety and security analysis, validation, and verification. The goal is to deliver research results that feature widely deployed, sustainable, and industry-ready open-source software.
Fraunhofer Institute for Experimental Software Engineering IESE