AI for Robotics (AIR-Lab)
At AIR-Lab, we approach robotics from two distinct yet complementary approaches that reflect the Cognitive Science and Artificial Intelligence focus areas of our Department: cognitive developmental robotics (CoDeRs) and deep learning (DL4Robotics).
dr. Murat KirtayPrincipal Investigator
dr. Giacomo SpiglerPrincipal Investigator
The CoDeRs approach integrates insights from various fields --including machine learning, interaction design, computational neuroscience, cognitive/developmental psychology, etc.-- to conduct interdisciplinary research in robotics and artificial intelligence.
Our goal is to develop computational models for embodied robots, both physical and virtual, that can interact with humans and other robots. As part of the CoDeRs team, we are also involved in the RoboCup Standard Platform.
In this research line, our ultimate aim is to help create human-robot symbiotic societies in an ethically responsible way.
The DL4Robotics line focuses on incorporating the latest advances in deep learning into robotics. We are particularly interested in the development of fully end-to-end robot learning methods based on deep reinforcement learning, imitation learning, and self-supervised learning.
Our applications span a variety of domains, including human-robot interaction, together with CoDeRs, and dexterous manipulation, for which we use the in-lab developed Tilburg robot hand.
- University of Sheffield
- Italian Institute of Technology
- Osaka University, Symbiotic Intelligent Systems Research Center (SISReC)
- Scuola Superiore Sant’Anna, The BioRobotics Institute
- Humboldt University of Berlin