There has been a great deal of work on learning new robot skills, but very little consideration
of how these newly acquired skills can be integrated into an overall intelligent system. A key …

The objective of this work is to augment the basic abilities of a robot by learning to use
sensorimotor primitives to solve complex long-horizon manipulation problems. This requires …

In complex manipulation scenarios (eg tasks requiring complex interaction of two hands or
in-hand manipulation), generalization is a hard problem. Current methods still either require …

We describe a system allowing a robot to learn goal-directed manipulation sequences such
as steps of an assembly task. Learning is based on a free mix of exploration and instruction …

In this paper, we propose a formal language to specify robot skills, ie the elementary
behaviours or functions provided by the robot platform in order to perform an autonomous …

The effectiveness of robot interaction depends on the robot's ability to perform task-relevant
actions and on the degree to which it is able to predict the outcomes of these actions. In this …

We present a novel solution to the problem of simulation-to-real transfer, which builds on
recent advances in robot skill decomposition. Rather than focusing on minimizing the …

Programming by demonstration has recently gained much attention due to its user-friendly
and natural way to transfer human skills to robots. In order to facilitate the learning of …

In this paper we describe our approach to robotic skill representation and a prototypical
implementation of a programming-by-demonstration approach that allows users to generate …

A critical capability required for generally intelligent robot behavior is the ability to sequence
motor skills to reach a goal. This requires a (typically abstract) representation that supports …