Projects and products

The tools and concepts developed are intended to enable property managers and external service providers to optimize control loops (e.g., flow temperature setpoints) with minimal effort and in line with specific needs, and to immediately monitor the effectiveness of the measures.

A quantum rangefinder measures distances with precision using active illumination, which, however, remains hidden from third parties against a natural background.

The Karlsruher Forschungsfabrik for AI-integrated production offers the special opportunity to research and develop the topic of “Intelligent Production” in a practical way on real processes.

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.

ARGoS is an Intelligent Information Management for Coalition Shared Data (CSD). Our ARGoS approach enhances the existing metadata search in CSD servers with a unified multimodal search over product content. This enables users to search directly for relevant information within, for example, reconnaissance reports and imagery.

For the “Intelligent Video Surveillance“ project, Fraunhofer IOSB's VID department is developing a system that can detect possible crimes based on movement patterns and alert police officers in the command and situation center. Facial recognition is not part of the solution approach.

We develop and implement AI systems specifically designed for domains with strict security and compliance requirements. Our focus is on customized AI architectures that meet the highest standards of accuracy, transparency, and methodological traceability, enabling us to design data-driven processes that are both information-secure and efficient.

The ResilVerbund project focuses on the AI-supported monitoring and forecasting of biodiversity and water quality in drinking water reservoirs.

As part of the joint project iTEXFer, we are developing an expandable Industry 4.0 construction kit specifically tailored to the textile industry.

In the "InnoTeer" project, the Fraunhofer Institutes IBP, IML, IOSB and UMSICHT are now developing a multistage process to efficiently process tar-containing road debris in decentralized plants, because about 3.3 million tons of tar-containing road debris are produced in Germany every year: Two million tons of it end up in landfills.

Correct decisions are the result of accurate, precise knowledge of the situation and correct assessment of the options for action. The more urgent the situation is, the more difficult it is to react to and the less a second chance is to be expected.

Our Connector combines the benefits of Industrie 4.0 and International Data Spaces for interoperable, trusted and controlled data exchange.

The aim of the H2020 project is the digital management of production capacities for the development of flexible supply chains between consumers and producers - especially for rapid response to pandemics.

Our research focuses on optimizing sorting systems through the use of artificial intelligence (AI), in particular convolutional neural networks (CNNs), which outperform conventional image processing algorithms.

Concepts and procedures for the robust localization and navigation of underwater vehicles and for the realization of the planned inspection and exploration capabilities are developed.

The Potential pilot AI is a compact, modular solution that offers medium-sized companies a cost-effective way to evaluate the potential of AI processes in their production processes.

In this cooperation project, an intelligent system is to be designed and implemented as a prototype that enables the rapid detection and precise localization of leaks in district heating networks based on data and, based on this, calculates response strategies for shutting off network sections while ensuring an optimal supply to end customers.

Terrain evaluation in support of operation planning and battle management

The concept of self-calibration for each component of the triangulation sensor system within the object coordinate system enables highly precise measurement of even very large objects using a scalable multisensor system.

The internally funded project is aimed at developing a software-based system for defining dynamic safety zones. This should make it possible to fulfill functional safety requirements in modular, dynamically changing production environments in a way that saves time and money.