[WiSe 2025/26] Knowledge Graphs and AI-driven Applications

Learning Outcomes

In an increasingly data-driven world, making sense of complex, interconnected information is a key challenge across domains such as robotics, smart cities, automotive, and digital twins. Knowledge Graphs (KGs) have emerged as a powerful paradigm for structuring and reasoning over semantic data, enabling intelligent systems to integrate, interpret, and act upon diverse sources of information. This course offers a comprehensive introduction to the foundations, construction, storage, and AI-driven applications of Knowledge Graphs. Students will explore both theoretical underpinnings and practical implementations, gaining the skills needed to apply knowledge graphs effectively in cutting-edge AI systems powered by large language models (LLMs) and foundation models. Through real-world examples and hands-on exercises, participants will learn how to build scalable, dynamic, and context-aware knowledge systems that bridge symbolic reasoning and machine learning. In summary, learning objectives include: - Demonstrate fundamental and practical knowledge of Knowledge Graphs. - Demonstrate skills in applying Knowledge Graphs in AI-driven applications in Robotics, Automotive, Smartcities.
 
Lesson Plan:
 

Lesson 1: Introduction and logistics 

Lesson 2: Foundation and Concepts (RDF, SPARQL, SCHACL, Reasoning) 

Lesson 3: Knowledge representation, Query and Storage

Lesson 4. Commonsense Knowledge and Perception

Lesson 5. Industrial Ontologies and Standards

Lesson 6. KG in Robotics

Lesson 7. KG Automotive 

Lesson 8. KG Smart Cities and Digital Twins

Lesson 9. Uncertainty and Learning

Lesson 10. Knowledge Acquisition and Construction 

Lesson 11. Advanced applications and Challenges 

Lesson 12. Project presentations and Oral exams