Robots Learning Through Interactions

How can robots learn complex skills faster?
The acquisition and self-improvement of novel motor skills is among the most important problems in robotics. Complexity arises from interactions with their environment and humans, dealing with high-dimensional input data, non-linear dynamics in general and contacts in particular, multiple reference frames, and variability in objects, environments, tasks, and human behavior. A human teacher is always involved in the learning process, either directly (providing data) or indirectly (designing the optimization criterion),
This talk shows that there are enormous advantages to having a human teacher interact with a robot at times during the learning process. Various methods from the fields of supervised learning, imitation learning, reinforcement learning, and interactive learning will be discussed.
All the concepts will be illustrated with benchmark tasks and real robot experiments ranging from fun (ball-in-a-cup) to more applied (retail environments).

Speaker: Jens Kober, TU Delft

This talk is part of the public IfI Colloquium series: https://www.ifi.uzh.ch/en/studies/phd/colloquium/spring-2026.html#Kober

You may also like the following events from University of Zurich, Department of Informatics:

• This month, 19th March, 05:15 pm, Cognitive Scaffolding in the Age of AI: Design Principles for Appropriate Reliance in Zurich
• This May, 7th May, 05:15 pm, Human-Centric Machine Learning: Transparency, Explainability, and Guidance by Human Feedback in Zurich
• This May, 21st May, 05:15 pm, Drones and the Foundations of Political Authority in Zurich