ASCS Brochure #2025 - Magazine - Page 29
AI SIMULATION – FROM THE ASSEMBLY
LINE TO THE STREETS
QUALITY ASSURANCE WITH AI IN
PRODUCTION
AI simulation is also applied in vehicle manufacturing. The
AIQUAMA (AI-based Quality Management for Smart
Factories) project, funded by the Federal Ministry of
Research, Technology, and Space (BMFTR), explores the use
of artificial intelligence in quality management of production
processes. In a specific application scenario, the project
partners demonstrate how AI-driven quality assurance
supports accurate production steps in car body construction.
A key part of this is integrating the assembly process into a
digital twin that simulates the entire production scenario.
One application example is the vehicle door assembly
process, where adjusting the gap size is a complex challenge.
The demonstrator created in the project combines sensor
technology, digital twins, and AI to develop an adaptive
quality assurance system. Deviations are automatically
detected and visually displayed to the worker via mixed
reality glasses or projections on the component.
The system also analyzes the context – such as a worker's
movement or the status of an assembly step – and provides
specific recommendations for action. All data is synchronized
in an administration shell, allowing the system to be actively
integrated into the process chain.
DFKI's research demonstrates how generative AI,
simulation-based decision models, and explainable
processes can be combined to create an end-to-end
simulation chain. By integrating explainable, data-driven, and
generative components, DFKI makes significant contributions
to the next generation of safe and comprehensible AI
systems in road traffic. Using intelligent sensor technology,
digital twins, and adaptive algorithms, DFKI is paving the way
for resilient, AI-supported manufacturing processes in the
automotive industry. Through close collaboration with
industry partners, the integration of these methods into
industrial workflows was considered from the start. With its
expertise in simulation, DFKI is making a substantial
contribution to developing reliable, understandable, and
efficient AI systems in the automotive sector.
AUTHORS
Dr. Christian Müller, Head of Competence Center
Autonomous Driving, DFKI
Dr. Daniel Porta, Project Manager AIQUAMA
The German Research Center for Artificial Intelligence
(DFKI) has operated as a non-profit, Public-PrivatePartnership (PPP) since 1988. Today, it maintains sites
in Kaiserslautern, Saarbrücken, Bremen, Niedersachsen, and Darmstadt, laboratories in Berlin, and
Lübeck, as well as a branch office in Trier.
DFKI combines scientific excellence and commerciallyoriented value creation with social awareness and is
recognized as a major "Center of Excellence" by the
international scientific community. In the field of
artificial intelligence, DFKI has focused on the goal of
human-centric AI for more than 35 years. Research is
committed to essential, future-oriented areas of
application and socially relevant topics. Currently, with
a staff of about 1,560 employees from more than 76
countries, DFKI is developing the innovative software
technologies of tomorrow.
www.dfki.de
29
