-
Article
Open AccessModularity in Nervous Systems—a Key to Efficient Adaptivity for Deep Reinforcement Learning
Modularity as observed in biological systems has proven valuable for guiding classical motor theories towards good answers about action selection and execution. New challenges arise when we turn to learning: T...
-
Chapter and Conference Paper
From Geometries to Contact Graphs
When a robot perceives its environment, it is not only important to know what kind of objects are present in it, but also how they relate to each other. For example in a cleanup task in a cluttered environment...
-
Article
“KogniChef”: A Cognitive Cooking Assistant
Cooking is a complex activity of daily living that requires intuition, coordination, multitasking and time-critical planning abilities. We introduce KogniChef, a cognitive cooking assistive system that provides u...
-
Chapter and Conference Paper
Tactile Convolutional Networks for Online Slip and Rotation Detection
We present a deep convolutional neural network which is capable to distinguish between different contact states in robotic manipulation tasks. By integrating spatial and temporal tactile sensor data from a pie...
-
Chapter and Conference Paper
Learning Gestalt Formations for Oscillator Networks
The binding of similar objects to a common group is an effortless task for humans.We know if things belong together or not by intuitively relying on a set of rules. In the area of visual perception, these rule...
-
Chapter and Conference Paper
Learning of Lateral Interactions for Perceptual Grou** Employing Information Gain
Perceptual Grou** is an important aspect in the understanding of sensory input. One of the major problems there is, how features can form meaningful groups while segregating from non relevant informations. O...
-
Article
Self-Organizing Feature Maps for Modeling and Control of Robotic Manipulators
This paper presents a review of self-organizing feature maps (SOFMs), in particular, those based on the Kohonen algorithm, applied to adaptive modeling and control of robotic manipulators. Through a number of ...