Machine Learning and Robotics

The field of Machine Learning (ML) can be understood as a science of learning systems. While the neurosciences and psychology aim to describe mechanisms of learning in humans and animals, Machine Learning aims to develop algorithms that demonstrate the ability to learn from data and improve with experience. Machine Learning has become a central subdiscipline of Artificial Intelligence and utilizes methods from statistical learning theory for efficient data analysis. In particular the great success of ML for data analysis has led to  its application in many commercial and scientific applications, e.g., becoming a central tool for the dominant IT companies to exploit their data as well as for applications in bioinformatics and the neurosciences.

The Machine Learning & Robotics (MLR) Lab aims to push Machine Learning methods towards intelligent real world systems, in particular robots learning to interact with and manipulate their environment. Unlike standard data analysis methods, the system needs to actively collect data and derive models of the environment that enable goal-directed decision making and planning. Research questions that arise are: How can an autonomous agent learn to act in a goal-directed way in environments of everyday life such as kitchens and offices?  What are appropriate representations for efficient reasoning about actions and goals?

Technically, the MLR Lab focusses on the areas of

• Reinforcement learning
• Probabilistic modelling and inference
• Relational representations

and their application in Robotics. A core question we have in mind is learning appropriate representations to formulate and learn models of the environment on an abstract level. Please visit our publications and projects for more details.