Projects and products of the Cognitive Industrial Systems department

Cancel
  • LLM4OPC enables interaction with industrial systems via a secure, natural language interface. Through OPC UA and Asset Administration Shells (AAS), connected via the Model Context Protocol (MCP), Large Language Models (LLMs) can read live machine data, explain machine statuses in an understandable way, and - upon approval - execute actions.

    more info
  • SWAP – heterogeneous, workload-optimised robot teams and production architectures

    Hierarchical swarms working together (semi-)autonomously: As part of the SWAP lighthouse project, ten Fraunhofer Institutes are developing new technological concepts for the modular and self-organized production of the future.

    In the Fraunhofer SWAP lighthouse project, ten Fraunhofer institutes are developing technological concepts for the modular and self-organised production of the future, which will no longer be controlled centrally but decentrally - all the way to hierarchical swarms whose participants work together collaboratively and (partially) autonomously.

    more info
  • Factory-X – a sovereign data room for mechanical and industrial engineering

    An open data ecosystem for factory equipment suppliers and their customers - on the foundations of Industrie 4.0 and Gaia-X/Catena-X

    In the lighthouse project Factory-X, an open and collaborative data ecosystem for factory outfitters and operators is being developed on the basis of Catena-X and concepts of the Industry 4.0 platform. Fraunhofer IOSB is involved in or leading a number of use cases.

    more info
  • Wool, Cotton, Warping Machine, Thread, Bobbin

    The production of high-performance carding assemblies for the textile industry is extremely complex and requires a high degree of precision. The “Machine Learning for Textile Industry” (ML4Tex) project optimizes this process by predicting the quality of the final product during production.

    more info
  • Humanoid Robots Experience Lab

    From Experience to Application: We offer a “hands-on” approach to humanoid robotics –
    as a foundation for developing concrete use cases and roadmaps

    Whether you’re a pioneer from industry, an SME, a skilled-trades business, the municipal or government sector, or an emergency services organization: As the Fraunhofer IOSB’s Humanoid Robots Experience Lab (HREL), we offer you low-threshold, hands-on access to humanoid robotics.

    more info
  • RICE – AI-supported process optimization simplified

    Rapid Instrumentation and Control Environment

    © Fraunhofer IOSB / M. Zentsch

    The RICE project was launched as part of the technology development program to develop tools that can collect plant data in a minimally invasive manner and actively intervene in processes. The long-term goal is to improve the efficiency of industrial manufacturing systems.

    more info
  • CHAISE - AI engineering made practical with the Tool Chain for AI Systems Engineering

    A toolbox to continuously improve and deploy ML applications (MLOps)

    © Fraunhofer IOSB (with material from stock.adobe.com)

    Operating machine learning applications productively requires continuous monitoring, adaptation, and maintenance.

    A project of the same name aims to harness our experience across a whole host of AI application domains to realize MLOps with maximum effectiveness and automate it as far as possible. To that end a software suite was developed that incorporates a wide range of tools for creating machine learning applications and training the ML models.

    more info