Daniel Kappler

Learn More
We propose a new large-scale database containing grasps that are applied to a large set of objects from numerous categories. These grasps are generated in simulation and are annotated with different grasp stability metrics. We use a descriptive and efficient representation of the local object shape at which each grasp is applied. Given this data, we present(More)
In this work, we present a new software environment for the comparative evaluation of algorithms for grasping and dexterous manipulation. The key aspect in its development is to provide a tool that allows the reproduction of well-defined experiments in real-life scenarios in every laboratory and, hence, benchmarks that pave the way for objective comparison(More)
One of the main challenges in autonomous manipulation is to generate appropriate multi-modal reference trajectories that enable feedback controllers to compute control commands that compensate for unmodeled perturbations and therefore to achieve the task at hand. We propose a data-driven approach to incrementally acquire reference signals from experience(More)
Learning of inverse dynamics modeling errors is key for compliant or force control when analytical models are only rough approximations. Thus, designing real time capable function approximation algorithms has been a necessary focus towards the goal of online model learning. However, because these approaches learn a mapping from actual state and acceleration(More)
In this paper, we present a method for representing and re-targeting manipulations for object adjustment before final grasping. Such pre-grasp manipulation actions bring objects into better configurations for grasping through e.g. object rotation or object sliding. For this purpose, we propose a scaling-invariant and rotation-invariant representation of the(More)
In manipulation tasks that require object acquisition, pre-grasp interaction such as sliding adjusts the object in the environment before grasping. This change in object placement can improve grasping success by making desired grasps reachable. However, the additional sliding action prior to grasping introduces more complexity to the motion planning(More)
Parametric filters, such as the Extended Kalman Filter and the Unscented Kalman Filter, typically scale well with the dimensionality of the problem, but they are known to fail if the posterior state distribution cannot be closely approximated by a density of the assumed parametric form.
The Gaussian Filter (GF) is one of the most widely used filtering algorithms; instances are the Extended Kalman Filter, the Unscented Kalman Filter and the Divided Difference Filter. GFs represent the belief of the current state by a Gaussian with the mean being an affine function of the measurement. We show that this representation can be too restrictive(More)
While grasping and manipulation in highly-controlled scenarios such as in factories is already possible, it remains unclear how a robot can achieve this autonomously in realworld scenarios that are characterized by a high degree of uncertainty. This uncertainty can be attributed to partial and noisy observations, a dynamic, constantly changing world and(More)
It has long been hoped that model-based control will improve tracking performance while maintaining or increasing compliance. This hope hinges on having or being able to estimate an accurate inverse dynamics model. As a result, substantial effort has gone into modeling and estimating dynamics (error) models. Most recent research has focused on learning the(More)