The Aalto Robot Learning Research Group operates at the intersection of artificial intelligence and robotics. We focus on reinforcement learning, robotic manipulation, decision making under partial observability, imitation learning, and decision making in multi-agent systems.

We envision a world where autonomous robots can solve complex tasks in unknown and unstructured environments, for example, cleaning up toys, arranging objects in a kitchen, segregating waste or lifting tree trunks onto a truck. To accomplish this, a robot needs to jointly learn about the environment whilst performing its assigned tasks. This is especially challenging in environments such as homes because objects occlude each other.

Our goal is to make robots capable of operating autonomously alongside humans, by helping them understand what they need to learn in order to perform their assigned tasks. To this end, we focus on developing novel decision making methods for solving previously unsolved robotics tasks. In particular, we develop methods for reinforcement learning, planning under uncertainty, and decision making in multi-agent systems.