• Publications
  • Influence
Leveraging big data for grasp planning
TLDR
A deep learning method is applied and it is shown that it can better leverage the large-scale database for prediction of grasp success compared to logistic regression and suggest that labels based on the physics-metric are less noisy than those from the υ-metrics and therefore lead to a better classification performance. Expand
Riemannian Motion Policies
TLDR
RMPs are easy to implement and manipulate, simplify controller design, clarify a number of open questions around how to effectively combine existing techniques, and their properties of geometric consistency make feasible the generic application of a single smooth and reactive motion generation system across a range of robots with zero re-tuning. Expand
Superpixel Convolutional Networks Using Bilateral Inceptions
TLDR
A new “bilateral inception” module that can be inserted in existing CNN architectures and performs bilateral filtering, at multiple feature-scales, between superpixels in an image. Expand
Data-Driven Online Decision Making for Autonomous Manipulation
TLDR
A data-driven approach to incrementally acquire reference signals from experience and decide online when and to which successive behavior to switch, ensuring successful task execution and is robust against perturbation and sensor noise. Expand
Towards robust online inverse dynamics learning
TLDR
The online adapted offset term ensures good tracking such that a nonlinear function approximator is able to learn an error model on the desired trajectory, and creates a controller with variable feedback and low gains, and a feedforward model that can account for larger modeling errors. Expand
Self-supervised regrasping using spatio-temporal tactile features and reinforcement learning
One of the central tasks for a household robot is searching for specific objects. It does not only require localizing the target object but also identifying promising search locations in the scene ifExpand
Leveraging Contact Forces for Learning to Grasp
TLDR
This paper uses model-free deep reinforcement learning to synthesize control policies that exploit contact sensing to generate robust grasping under uncertainty and suggests that contact feedback allows for a significant improvement of grasping robustness under object pose uncertainty and for objects with a complex shape. Expand
Real-Time Perception Meets Reactive Motion Generation
TLDR
This work extensively evaluates the systems on a real robotic platform in four scenarios that exhibit either a challenging workspace geometry or a dynamic environment and quantifies the robustness and accuracy that is due to integrating real-time feedback at different time scales in a reactive motion generation system. Expand
Representation of pre-grasp strategies for object manipulation
TLDR
It is shown that pre-grasp strategies such as sliding manipulations not only enable more robust object grasping, but also significantly increase the success rate for grasping. Expand
A new perspective and extension of the Gaussian Filter
TLDR
This work views the Gaussian Filter as a special case of a much broader class of filters, obtained by relaxing the constraint on the form of the approximate posterior, and outlines some conditions which potential generalizations have to satisfy in order to maintain the computational efficiency of the GF. Expand
...
1
2
3
4
...