Sort by:

• Highly Influential Citations
• Citations
• Acceleration
• Velocity
• Recency

Learn More

State Representation Learning in Robotics: Using Prior Knowledge about Physical Interaction

• Rico Jonschkowski, Oliver Brock
• Robotics: Science and Systems
• 2014

—State representations critically affect the effectiveness of learning in robots. In this paper, we propose a robotics-specific approach to learning such state representations. Robots accomplish tasks by interacting with the physical world. Physics in turn imposes structure on both the changes in the world and on the way robots can effect these changes.… (More)

Lessons from the Amazon Picking Challenge: Four Aspects of Building Robotic Systems

• Clemens Eppner, Sebastian Höfer, +4 authors Oliver Brock
• Robotics: Science and Systems
• 2016

—We describe the winning entry to the Amazon Picking Challenge. From the experience of building this system and competing in the Amazon Picking Challenge, we derive several conclusions: 1) We suggest to characterize robotic system building along four key aspects, each of them spanning a spectrum of solutions—modularity vs. integration, generality vs.… (More)

Lessons from the Amazon Picking Challenge: Four Aspects of Robotic Systems Building

• Clemens Eppner, Sebastian Höfer, +5 authors Roberto Martin Martin
• 2016

—We describe the winning entry to the Amazon Picking Challenge. From the experience of building this system and competing in the Amazon Picking Challenge, we derive several conclusions: 1) We suggest to characterize robotic systems building along four key aspects, each of them spanning a spectrum of solutions—modularity vs. integration, generality vs.… (More)

Learning state representations with robotic priors

• Rico Jonschkowski, Oliver Brock
• Auton. Robots
• 2015

Robot learning is critically enabled by the availability of appropriate state representations. We propose a robotics-specific approach to learning such state representations. As robots accomplish tasks by interacting with the physical world, we can facilitate representation learning by considering the structure imposed by physics; this structure is… (More)

Probabilistic multi-class segmentation for the Amazon Picking Challenge

• Rico Jonschkowski, Clemens Eppner, Sebastian Höfer, Roberto Martin Martin, Oliver Brock
• 2016 IEEE/RSJ International Conference on…
• 2016

We present a method for multi-class segmentation from RGB-D data in a realistic warehouse picking setting. The method computes pixel-wise probabilities and combines them to find a coherent object segmentation. It reliably segments objects in cluttered scenarios, even when objects are translucent, reflective, highly deformable, have fuzzy surfaces, or… (More)

Learning Task-Specific State Representations by Maximizing Slowness and Predictability

• Rico Jonschkowski, Oliver Brock
• 2013

The success of reinforcement learning in robotic tasks is highly dependent on the state representation – a mapping from high dimensional sensory observations of the robot to states that can be used for reinforcement learning. Even though many methods have been proposed to learn state representations, it remains an important open problem. Identifying the… (More)

Contextual Learning

• Rico Jonschkowski, Sebastian Höfer, Oliver Brock
• ArXiv
• 2015

New Approaches to Temporal Abstraction in Hierarchical Reinforcement Learning

• Rico Jonschkowski, Marc Toussaint
• 2012

In classical reinforcement learning, planning is done at the level of atomic actions, which is highly laborious for complex tasks. By using temporal abstraction, an agent can construct plans more eciently through considering dierent levels of detail. This thesis investigates new approaches to automatically discover and represent temporal abstractions. Two… (More)

Patterns for Learning with Side Information

• Rico Jonschkowski, Sebastian Hofer, Oliver Brock
• 2015

Supervised, semi-supervised, and unsupervised learning estimate a function given input/output samples. Generalization of the learned function to unseen data can be improved by incorporating side information into learning. Side information are data that are neither from the input space nor from the output space of the function, but include useful information… (More)

PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations

• Rico Jonschkowski, Roland Hafner, Jonathan Scholz, Martin A. Riedmiller
• ArXiv
• 2017

We propose position-velocity encoders (PVEs) which learn—without supervision—to encode images to positions and velocities of task-relevant objects. PVEs encode a single image into a low-dimensional position state and compute the velocity state from finite differences in position. In contrast to autoencoders, position-velocity encoders are not trained by… (More)

• ‹
• 1
• ›