Data-driven methods are reshaping advanced engineering practice and research across domains such as intelligent product design, production systems, robotics, and other technical fields, requiring the ability to integrate machine learning, optimization, and simulation in complex systems.

In this project, students work independently in small teams on a complex, data-driven engineering problem. The focus is on identifying and formulating a challenging research- or application-oriented task, selecting and combining advanced methods from machine learning, optimization, and simulation, and critically evaluating the results. Students are expected to incorporate and build upon the research results in their methods and solutions. 

Using modern software frameworks and computational resources (e.g., Isaac Sim, PyTorch, scikit‑learn, distributed or cluster computing environments), students design, implement, and evaluate sophisticated data-driven engineering solutions for one of the above-mentioned domains. Results are documented in an appropriate format (e.g., a written report or comparable documentation) and presented through oral presentations, complemented by short project videos or pitch formats.

The course is conducted primarily on-site to support collaboration, supervision, and access to technical resources. Good Python programming skills are expected. Students should be prepared to independently work with and extend their knowledge of operating systems and tools such as Linux and Docker.

Learning Objectives

After successful completion of the project, students will be able to:

• Identify, formulate, and analyze complex engineering problems as data-driven tasks, and justify the selection of methods and tools.
• Design, implement, and optimize data-driven solutions using advanced machine learning, optimization, and simulation techniques.
• Critically evaluate and defend findings and methodological choices effectively, including reports, presentations, and multimedia formats.

Additional Information

The number of participants is limited. Information on the application process is available in ILIAS.

Organizational Information

See further details on course organization at: lehre.imi.kit.edu and in ILIAS

Workload

120 hours

Time and Location see ILIAS