Deep reinforcement learning augments the reinforcement learning framework and utilizes
the powerful representation of deep neural networks. Recent works have demonstrated the …

The virtual-to-real paradigm, ie, training models on virtual data and then applying them to
solve real-world problems, has attracted more and more attention from various domains by …

Image segmentation is often ambiguous at the level of individual image patches and
requires contextual information to reach label consensus. In this paper we introduce …

In this work, we present a data-driven simulation and training engine capable of learning
end-to-end autonomous vehicle control policies using only sparse rewards. By leveraging …

Simulation-to-real domain adaptation for semantic segmentation has been actively studied
for various applications such as autonomous driving. Existing methods mainly focus on a …

End-to-end approaches to autonomous driving have high sample complexity and are difficult
to scale to realistic urban driving. Simulation can help end-to-end driving systems by …

In this paper, we present a joint multi-task learning framework for semantic segmentation
and boundary detection. The critical component in the framework is the iterative pyramid …

What is a good visual representation for navigation? We study this question in the context of
semantic visual navigation, which is the problem of a robot finding its way through a …

Robots that autonomously navigate real-world 3D cluttered environments need to safely
traverse terrain with abrupt changes in surface normals and elevations. In this letter, we …

We show how to use the Operational Space Control framework (OSC) under joint and
Cartesian constraints for reinforcement learning in Cartesian space. Our method is able to …