Digital training Fraunhofer: AI-Powered Learning Management System for the Bundeswehr

Related Vendors

GGB Heilbronn GmbH

Fastems Systems GmbH

Artificial Intelligence is set to optimally support soldiers in their learning processes and enhance the quality of instruction. In a study, researchers from Fraunhofer identified which AI functionalities are useful and how they can be technically integrated into the existing system.

In the future, the Bundeswehr aims to create a virtual learning environment for all personnel. To further their education in various fields, such as mathematics, English, or social skills, soldiers currently use conventional learning management systems like Moodle to prepare efficiently for exams. Researchers at Fraunhofer have tested how AI can be integrated into this system and which applications would be helpful in a collaborative project.

Initial tests impress soldiers

To determine whether and what added value can be created using AI, Daniela Altun, project leader and research associate at the Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE, and her team accompanied a training course as a case study. Researchers from the Fraunhofer Institutes for Optronics, System Technology and Image Exploitation IOSB, as well as for Open Communication Systems FOKUS, were also involved in the collaborative project.

The team initially conducted a requirements analysis and surveyed various stakeholders, including learners, instructors, supervisors, and course planners, regarding the desired AI tools. The feedback was then organised in the form of user stories. In the final step, the researchers examined which of the mentioned features could be realised and how users could benefit from them.

Company profile

The Sovereign Constellation: OHB SE and OHB Digital Connect

A mix of AI functionalities was tested: For instance, a specially developed chatbot that operates similarly to ChatGPT but is suitable for handling sensitive data due to its closed network. Additionally, the chatbot provides quality-checked answers, as long as these have been provided by the course leader, and can display sources when needed.

The researchers also integrated a competence assessment app (KoApp) on a trial basis, which synchronises with the learning management system. In the training course supported by the study, no grades are awarded; instead, the training is competency-oriented. Until now, a suitable assessment framework has often been lacking. The KoApp aims to address this by visually representing the competencies of the soldiers in diagram format. Course leaders can view the individual learning progress and provide targeted support to participants.

Thanks to a dashboard, instructors also received an overview statistic of the knowledge level of the respective course. Additionally, a personal AI learning path offered study participants the opportunity to tackle learning content in a different sequence than originally specified by the course leader. A learning recommendation system with an integrated progress indicator was also tested.

Europe’s security landscape is changing rapidly

As defence budgets rise and EU programmes expand, civil technology providers are becoming vital contributors to Europe’s strategic autonomy. The event will act as a neutral platform for dialogue between technology suppliers, integrators, and decision-makers shaping the next generation of European defence capabilities and aims to open doors between civil industry and defence procurement, providing practical insights.

Find out more and register

"As the AI adapts to the individual learning progress, users of the tool will neither be overstretched nor underwhelmed," says project leader Altun. "This is intended not only to enhance the quality of teaching but also to increase the enjoyment of learning."

The test results show that the chatbot was particularly well received by users, primarily being used for referencing and filtering lengthy regulations. Many participants praised its intuitive usability.

In addition to the various AI features, the project also utilised a "common learning middleware," which had already been developed by Fraunhofer researchers. This special software facilitates communication between AI functionalities that are based on different data standards and enables their integration into the learning management system.

In a potential follow-up study, the Fraunhofer researchers aim to consider additional users and educational institutions. Project leader Daniela Altun is looking forward to the continuation of the project: "In the long term, we want to promote lifelong learning with the help of this tool. The artificial intelligence will always remain an optional offering and is intended to optimally support instructors, not replace them."