Teaching Winter 2024/2025

Students will present papers from a list of important recent works in machine learning compiled by the professor. Topics include deep and reinforcement learning, and transformer and GNN architectures. The focus will be in the use of these techniques in simple applications that are crisp and easy to understand. The list of papers will also include those underlying well-known learning systems like as Dalle-E, ChaptGPT, Alphazero, Gato, etc.

Task and Motion Planning (TAMP) deals with combining high-level decision making with low-level manipulation in robotics. In the lab course, we implement and evaluate multiple state-of-the-art TAMP approaches in a domestic service robot scenario. You will learn about key concepts of robotics such as task planning with PDDL, motion planning algorithms, as well as integrated task and motion planning (TAMP).

The course is devoted to unpack basic questions like: How to make technology work for us? Has it worked for us in the past? Will it work for us in the future? Is there a monolithic “us”? What is actually what we want, collectively and individually? How do we act, collectively and individually? We cannot answer these questions without knowing some history, economics, politics, psychology, and evolutionary biology. In the course, we will make such a tour, and in parts, we will draw on bits of probability, causality, and game theory, to sharpen our critical thinking skills.