THA_air

Artificial Intelligence and Decision Making

Advanced machine learning methods, symbolic and neuro-symbolic reasoning, and planning-based approaches enable Physical AI systems to make robust, adaptive and transparent decisions in complex, uncertain and dynamic environments. In industrial applications and safety-critical systems, combining data-driven learning with explicit knowledge representation is essential for making decision processes more transparent, explainable and reliable.

Contact Prof. Dr.-Ing. Hon. Dr. of ONPU Thorsten Schöler
Computer Science HSA_ired
Phone:	+49 821 5586-3445
[Bitte aktivieren Sie Javascript]

Reference Projects

Research Kooperation

Projekt KI-HEAP4.0

Research project with F. X. MEILLER Fahrzeug- und Maschinenfabrik GmbH & Co. KG, GROB-WERKE GmbH & Co. KG, ITQ GmbH and OmegaLambdaTec GmbH

In the KI-HEAP4.0 project, the production system of an automotive component manufacturer is represented as a digital twin.

This digital twin serves as a simulation environment to support decision-making in detailed production scheduling, using a hybrid approach that combines mathematical optimization with reinforcement learning. ↗

Research Kooperation

Projekt DEXAI

Research project with inovex GmbH and RATIONAL AG

The DEXAI project develops resource-efficient and explainable methods for anomaly detection. The approach offers an alternative to data-intensive black-box models and makes results more transparent and traceable in technical applications. ↗

Research Kooperation

Projekt AIGS3D

Research project with CADdent® GmbH

The AIGS3D project develops methods for automatically generating support structures for 3D-printed objects in dental technology. Machine learning techniques are used to adapt the support structures to the geometric requirements of each component. ↗

Research Kooperation

Projekt LunKItekt

Research project with inno-focus digital GmbH

The LunKItekt project develops AI-based methods for detecting material defects on workpiece surfaces and monitoring tool wear during machining. The aim is to improve component quality while making more efficient use of resources.

↗

Publications

Übersicht Publikationen