In robotic tasks, changes in reference frames typically do not influence...
Extensive work has demonstrated that equivariant neural networks can
sig...
Differentiable planning promises end-to-end differentiability and adapti...
Behavior cloning of expert demonstrations can speed up learning optimal
...
We study how group symmetry helps improve data efficiency and generaliza...
Compositional generalization is a critical ability in learning and
decis...
To enable robots to instruct humans in collaborations, we identify sever...
Reinforcement learning is hard in general. Yet, in many specific
environ...
In robot navigation, generalizing quickly to unseen environments is
esse...
In robotics, it is often not possible to learn useful policies using pur...
We present a deep imitation learning framework for robotic bimanual
mani...
Abstraction is crucial for effective sequential decision making in domai...
Robots operating alongside humans in diverse, stochastic environments mu...
Deep neural networks are able to solve tasks across a variety of domains...
Humans can ground natural language commands to tasks at both abstract an...
To accomplish tasks in human-centric indoor environments, robots need to...