• Publications
  • Influence
Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown Cameras
TLDR
This work is the first to learn the camera intrinsic parameters, including lens distortion, from video in an unsupervised manner, thereby allowing us to extract accurate depth and motion from arbitrary videos of unknown origin at scale. Expand
Learning state representations with robotic priors
TLDR
This work identifies five robotic priors and explains how they can be used to learn pertinent state representations, and shows that the state representations learned by the method greatly improve generalization in reinforcement learning. Expand
Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors
TLDR
This work presents differentiable particle filters (DPFs), a differentiable implementation of the particle filter algorithm with learnable motion and measurement models that encode the structure of recursive state estimation with prediction and measurement update that operate on a probability distribution over states. Expand
State Representation Learning in Robotics: Using Prior Knowledge about Physical Interaction
TLDR
It is shown that the method extracts task-relevant state representations from highdimensional observations, even in the presence of task-irrelevant distractions, and that the state representations learned by the method greatly improve generalization in reinforcement learning. Expand
What Matters in Unsupervised Optical Flow
TLDR
A new unsupervised flow technique is presented that significantly outperforms the previous unsuper supervised state-of-the-art and performs on par with supervised FlowNet2 on the KITTI 2015 dataset, while also being significantly simpler than related approaches. Expand
Lessons from the Amazon Picking Challenge: Four Aspects of Building Robotic Systems
TLDR
This work describes the winning entry to the Amazon Picking Challenge, and suggests to characterize robotic system building along four key aspects, each of them spanning a spectrum of solutions—modularity vs. integration, generality vs. assumptions, computation vs. embodiment, and planning vs. feedback. Expand
PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations
TLDR
Position-velocity encoders (PVEs) which learn---without supervision---to encode images to positions and velocities of task-relevant objects and compute the velocity state from finite differences in position are proposed. Expand
End-to-End Learnable Histogram Filters
TLDR
A differentiable implementation of histogram filters is proposed that encodes the structure of recursive state estimation using prediction and measurement update but allows the specific models to be learned end-to-end, i.e. in such a way that they optimize the performance of the filter, using either supervised or unsupervised learning. Expand
The Distracting Control Suite - A Challenging Benchmark for Reinforcement Learning from Pixels
TLDR
The experiments show that current RL methods for vision-based control perform poorly under distractions, and that their performance decreases with increasing distraction complexity, showing that new methods are needed to cope with the visual complexities of the real world. Expand
Lessons from the Amazon Picking Challenge: Four Aspects of Building Robotic Systems
TLDR
This work describes the winning entry to the Amazon Picking Challenge, and suggests to characterize robotic system building along four key aspects, each of them spanning a spectrum of solutions—modularity vs. integration, generality vs. assumptions, computation vs. embodiment, and planning vs. feedback. Expand
...
1
2
3
4
...