TopoART: A topology learning hierarchical ART network

M Tscherepanow - International Conference on Artificial Neural Networks, 2010 - Springer
In this paper, a novel unsupervised neural network combining elements from Adaptive
Resonance Theory and topology learning neural networks, in particular the Self-Organising …

A hierarchical ART network for the stable incremental learning of topological structures and associations from noisy data

M Tscherepanow, M Kortkamp, M Kammer - Neural Networks, 2011 - Elsevier
In this article, a novel unsupervised neural network combining elements from Adaptive
Resonance Theory and topology-learning neural networks is presented. It enables stable on …

Interactive incremental online learning of objects onboard of a cooperative autonomous mobile robot

S Hasler, J Kreger, U Bauer-Wersing - … 13–16, 2018, Proceedings, Part VII …, 2018 - Springer
Detecting objects and referring to them in a dialog is a crucial requirement for robotic
systems that cooperate with humans. For this, in an unrestricted natural environment the …

Teaching human poses interactively to a social robot

V Gonzalez-Pacheco, M Malfaz, F Fernandez… - Sensors, 2013 - mdpi.com
The main activity of social robots is to interact with people. In order to do that, the robot must
be able to understand what the user is saying or doing. Typically, this capability consists of …

[인용][C] Developmental robotics: From babies to robots

A Cangelosi, M Schlesinger - 2015 - MIT press

Learning information acquisition for multitasking scenarios in dynamic environments

C Karaoguz, T Rodemann, B Wrede… - IEEE Transactions on …, 2012 - ieeexplore.ieee.org
Real world environments are so dynamic and unpredictable that a goal-oriented
autonomous system performing a set of tasks repeatedly never experiences the same …

Reward-based learning of optimal cue integration in audio and visual depth estimation

C Karaoguz, TH Weisswange… - 2011 15th …, 2011 - ieeexplore.ieee.org
Many real-world applications in robotics have to deal with imprecisions and noise when
using only a single information source for computation. Therefore making use of additional …

An analysis of depth estimation within interaction range

C Karaoguz, A Dankers, T Rodemann… - 2010 IEEE/RSJ …, 2010 - ieeexplore.ieee.org
Interactions between humans or humanoids and their environment through tasks like
gras** or manipulation typically require accurate depth information. The human vision …

Intelligent system architectures-comparison by translation

B Dittes, C Goerick - 2011 IEEE/RSJ International Conference …, 2011 - ieeexplore.ieee.org
System architectures are a central element to enable construction of increasingly complex
software systems for intelligent artifacts. Scientific discourse about such architectures …

Optimisation of gaze movement for multitasking using rewards

C Karaoguz, T Rodemann… - 2011 IEEE/RSJ …, 2011 - ieeexplore.ieee.org
Domestic tasks such as gras** or navigation for robotic systems can be supported by
vision. However, the environment provides a vast amount of visual information and …