FG Robotics

10 Items

Recent Submissions
EPSILON-CP: using deep learning to combine information from multiple sources for protein contact prediction

Stahl, Kolja ; Schneider, Michael ; Brock, Oliver (2017-06-17)

Background Accurately predicted contacts allow to compute the 3D structure of a protein. Since the solution space of native residue-residue contact pairs is very large, it is necessary to leverage information to identify relevant regions of the solution space, i.e. correct contacts. Every additional source of information can contribute to narrowing down candidate regions. Therefore, recent met...

Learning robotic perception through prior knowledge

Jonschkowski, Rico (2018)

Intelligent robots must be able to learn; they must be able to adapt their behavior based on experience. But generalization from past experience is only possible based on assumptions or prior knowledge (priors for short) about how the world works. I study the role of these priors for learning perception. Although priors play a central role in machine learning, they are often hidden in the deta...

No Free Lunch in Ball Catching: A Comparison of Cartesian and Angular Representations for Control

Höfer, Sebastian ; Raisch, Jörg ; Toussaint, Marc ; Brock, Oliver (2018)

How to run most effectively to catch a projectile, such as a baseball, that is flying in the air for a long period of time? The question about the best solution to the ball catching problem has been subject to intense scientific debate for almost 50 years. It turns out that this scientific debate is not focused on the ball catching problem alone, but revolves around the research question what c...

Leveraging problem structure in interactive perception for robot manipulation of constrained mechanisms

Martín-Martín, Roberto (2018)

In this thesis we study robot perception to support a specific type of manipulation task in unstructured environments, the mechanical manipulation of kinematic degrees of freedom. In these tasks the goal of the robot is to create controlled motion, i.e. to change configuration of the kinematic degrees of freedom (DoF) of the objects in the environment. Often, the environment contains articulate...

Exploitation of environmental constraints in human and robotic grasping

Eppner, Clemens ; Deimel, Raphael ; Álvarez-Ruiz, José ; Maertens, Marianne ; Brock, Oliver (2015)

We investigate the premise that robust grasping performance is enabled by exploiting constraints present in the environment. These constraints, leveraged through motion in contact, counteract uncertainty in state variables relevant to grasp success. Given this premise, grasping becomes a process of successive exploitation of environmental constraints, until a successful grasp has been establish...

Special Issue on the Sixteenth International Symposium on Robotics Research, 2013

Barfoot, Tim ; Brock, Oliver (2015)

null

A novel type of compliant and underactuated robotic hand for dexterous grasping

Deimel, Raphael ; Brock, Oliver (2016)

The usefulness and versatility of a robotic end-effector depends on the diversity of grasps it can accomplish and also on the complexity of the control methods required to achieve them. We believe that soft hands are able to provide diverse and robust grasping with low control complexity. They possess many mechanical degrees of freedom and are able to implement complex deformations. At the same...

Soft robotic hands for compliant grasping

Deimel, Raphael (2017)

The thesis considers the problem of grasping for autonomous robots, with a focus on the design and construction of robotic hands and grippers. The approach we take is to fundamentally reconsider the basic motivation and goals for grasping that steer hand design. We consider grasping as the result of reliable and robust patterns of interaction between hand, object and environment which are mecha...

On decomposability in robot reinforcement learning

Höfer, Sebastian (2017)

Reinforcement learning is a computational framework that enables machines to learn from trial-and-error interaction with the environment. In recent years, reinforcement learning has been successfully applied to a wide variety of problem domains, including robotics. However, the success of the reinforcement learning applications in robotics relies on a variety of assumptions, such as the availab...

RBO Hand 2 CAD Files

Deimel, Raphael ; Brock, Oliver (2016-03-31)

This dataset contains the CAD models for creating a RBO Hand 2. It consists of a set of molds that can be printed and used to create Pneuflex actuators, and a scaffold to attach actuators to in order to recreate the RBO Hand 2, a pneumatic soft hand developed by the Robotics and Biology Lab.