The ability to leverage heterogeneous robotic experience from different
...
Reinforcement learning (RL) has been shown to be effective at learning
c...
We study the problem of robotic stacking with objects of complex geometr...
We study how robots can autonomously learn skills that require a combina...
We propose a modular architecture for following natural language instruc...
Robots have the capability to collect large amounts of data autonomously...
All living organisms struggle against the forces of nature to carve out
...
Autonomous agents situated in real-world environments must be able to ma...
Convolutions on monocular dash cam videos capture spatial invariances in...
Well structured visual representations can make robot learning faster an...
While learning visuomotor skills in an end-to-end manner is appealing, d...
Robotic manipulation in complex open-world scenarios requires both relia...
Neural language models learn word representations, or embeddings, that
c...
Neural language models learn word representations that capture rich
ling...