The Artificial Intelligence and Machine Learning group is one of the research groups of the Department of Information and Communication Technologies at the Universitat Pompeu Fabra (UPF) in Barcelona, Spain.

The group research covers a number of areas, including:

• Automated planning: is the model-based approach to intelligent behavior, where behavior is not programmed or learned, but is derived effectively from a model of the agent goals, and the way that the actions and sensors work in the world.
• Interactive machine learning: is a branch of machine learning concerned with sequential decision-making problems, where the goal is designing algorithms that optimize performance during the learning procedure itself, while facing an unknown and potentially non-stationary environment.
• Learning theory: is the science of analyzing machine learning problems and algorithms, with the goal of characterizing the hardness of various learning scenarios and constructing algorithms with provable performance guarantees.
• Probabilistic graphical models: are graph-based representations to encode compactly probability distributions over high-dimensional spaces. Our focus is on how to efficiently answer queries (inference) and how to learn the graph structure from data (learning).
• Autonomous robotics: including the development of complete software architectures as well as the creation of base methodologies and tools for new advanced features. We combine reactive behaviour and motion planning with task planning, and use reasoning mechanisms to create robotics systems for challenges like RoboCup. 
• Constraint Satisfaction Problems (CSPs): these problems consist of a set of variables, a domain of values than can be taken by the variables and a set of constraints specifying restrictions of the values that can be taken simultaneously by the variables. The task here is to decide whether there exist an assignment of variables to values satisfying all constraints.