Autonomous Planning and Decision-making

© AdobeStock

Artificial intelligence methods are ideally suited for modeling situations in planning and decision-making processes that would be too complex to model using traditional techniques. The focus here is on the integration of uncertainties, domain knowledge, and foresight in order to generate robust autonomous planning and decision systems are created.

The group "Autonomous Planning and Decision Making" is concerned with the development of intelligent systems for the automated control of heterogeneous systems––from the actuator of individual production machines to the production strategy in large networks of machines and plants. The goal is to develop AI-based models for representing system behavior and dynamics in a fast and efficient manner. These models build the foundation for the optimization of complex production processes. Our methods can be applied at all levels of the automation pyramid, so that machine processes can be designed in an automated way and optimized production strategies can be determined. The well-known disadvantages of “uncertain” AI are overcome by means of latest research findings, such as the incorporation of probabilistic uncertainties or the creation of explainable models. This ensures a reliable application in practice.



Improving data quality is the most important step towards maximizing automated production. With TRUMPF, the department is pursuing AI-based order tracking to identify potential bottlenecks in production and aid employees.


DigiBattPro 4.0 – BW

To digitize battery cell production, AI-based planning algorithms are essential. The focus is on both business aspects, such as the prediction of sales figures, and physical models.



In the electromobility sector, the ability to predict the condition of batteries based on past usage is an important factor. AI-based methods can assess a battery's state of health in a way that is understandable for humans.


AI-based production planning and control

In a collaboration between Porsche AG and Fraunhofer IPA, AI-based concepts for production planning and control are being developed. The aim is to improve the stability of customer order management and to offer customers maximum flexibility and transparency.