Projects

MORE (2020-2023; European Industrial Doctorate program, EU)

MORE is an innovative European Industrial Doctorate (EID) research and training programme. The first of its kind that will address the need for dramatic improvements in HDM machinery and fill the gap in related research and training. Eight early stage researchers (ESRs) will be equipped with a set of research skills including robotics, machine learning, energy systems, as well as transferable skills such as entrepreneurship and career management. The Learning for Intelligent Autonomous Robots research group is involved in ESR8.

ROBOLEAP (2018-2021; DFG Project at TU Darmstadt, Germany)

The goal of the ROBOLEAP (Robot learning to perceive, plan, and act under uncertainty) project is to develop reinforcement learning methods that allow robots to operate in unstructured partially observable real world environments found in household robotics, adaptive manufacturing, elderly care, handling dangerous materials, or even disaster scenarios such as Fukujima. Robots that can operate in such complex environments need data-driven reinforcement learning methods that can take uncertainty due to partial observability into account. To make reinforcement learning in partially observable robotic tasks feasible we will develop new memory representations which allow us to efficiently reuse experience with different kinds of policies. To enable long-term action selection, we will improve exploration and value propagation over long horizons: under partial observability the robot needs to execute information gathering actions which requires uncovering and propagating values over long horizons during policy optimization. Moreover, in partially observable settings the problem of assigning values to actions is amplified. To solve this problem we will give the robot additional side information during learning. We will evaluate these methodological advances by endowing a real robot with the ability to play Mikado, a task that exhibits all the main difficulties connected to partial observability. The robot has to deal with occlusions and partial information. It has to proactively test physical properties of Mikado sticks and integrate this knowledge into its manipulation skills to remove sticks from the heap.