Projects

A central focus of the AI Innovation Center is direct cooperation with industrial companies: Feasibility studies (Quick Checks) and projects to develop initial prototypes (Exploring Projects) of AI applications. In addition, consortium projects and innovation networks are aimed at cross-company exchange.

Optical quality control of surfaces

The defects in the thermal deformation of aircraft landing gear are detected by the SFS algorithm. The results can be further processed with AI algorithms and material defects can be visualized with suitable lighting.

Packing planning shipping carton

Automatic model-free specification of packing patterns for shipping cartons.
Automation of the packaging process for various objects.

Peg-Men: Flexible assembly under disturbance variables

Flexible assembly of sensitive valve needles is optimized using deep reinforcement learning and physics simulation. The aim is to automate repetitive processes in order to increase efficiency and precision.

Perception for automated handling of dimensionally stable components (AutoLab)

Automated handling of dimensionally unstable components optimizes assembly processes through AI-supported perception, handling and inspection to increase efficiency and quality in production.

Planning Bot

The aim is to identify AI applications to improve production program planning. Employees receive training to develop use cases and support implementation.

Predictive services

Machine learning is used to detect errors in the cutting process at an early stage. Data from log files and service reports enable reliable prediction and minimization of machine failures.

RoboJudge: Successful trial execution with AI

The combination of AI methods and simulation techniques enables the precise monitoring and improvement of assembly processes in order to drive forward automation in enclosure assembly.

Damage evaluation with machine learning

The final acceptance requirements for employees were reviewed with the help of UNAs. AI potentials were identified and suggested.

Damage evaluation of rockfalls with machine learning

The semi-automated labeling tool can identify objects in images and draw bounding boxes around the defective areas using Segment Anything. Although the dataset is limited, the object detection model has shown promising results and is expected to be further improved with a larger dataset.

Semantic navigation

The solution for semantic navigation improves the environmental perception of autonomous robots through AI-supported object recognition. This enables robots to navigate more efficiently and react according to the situation.