Creating autonomous robots that can actively explore the environment, acquire knowledge
and learn skills continuously is the ultimate achievement envisioned in cognitive and …

A fundamental challenge in teaching robots is to provide an effective interface for human
teachers to demonstrate useful skills to a robot. This challenge is exacerbated in dexterous …

The success of deep learning depends heavily on the availability of large datasets, but in
robotic manipulation there are many learning problems for which such datasets do not exist …

Human motion prediction is essential in human-robot interaction. Current research mostly
considers the joint dependencies but ignores the bone dependencies and their relationship …

Capturing scene dynamics and predicting the future scene state is challenging but essential
for robotic manipulation tasks, especially when the scene contains both rigid and …

In this letter, we propose and realize a new deep learning architecture for discovering
symbolic representations for objects and their relations based on the self-supervised …

Pushing is an essential non-prehensile manipulation skill used for tasks ranging from pre-
grasp manipulation to scene rearrangement, reasoning about object relations in the scene …

Humans excel at performing a wide range of sophisticated tasks by leveraging skills
acquired from prior experiences. This characteristic is especially essential in robotics …

For multi-step robotic manipulation, it is important but challenging to predict the future state
of the object conditioned on the applied action, especially from the original sensory …

The success of deep learning depends heavily on the availability of large datasets, but in
robotic manipulation there are many learning problems for which such datasets do not exist …