Gökhan Ince, Kazuhiro Nakadai, Tobias Rodemann, Hiroshi Tsujino, Jun-ichi Imura,
"Whole Body Motion Noise Cancellation of a Robot for Improved Automatic Speech Recognition",
Advanced Robotics, vol. 25, no. 14, 2011.
Abstract
The motors of a robot produce ego-motion noise that degrades the quality of recorded sounds. This article describes an architecture that enhances the capability of a robot to perform automatic speech recognition (ASR) even as the entire body of the robot moves. The architecture consists of three blocks: (1) a multi-channel noise reduction block, consisting of microphone-array-based sound localization, geometric source separation and post-ltering,...
Download Bibtex file
Download PDF
Rujiao Yan, Tobias Rodemann, Britta Wrede,
"Learning of Audiovisual Integration",
Proceedings of ICDL/EPIROB 2011, 2011.
Abstract
We present a system for learning audiovisual integration based on temporal and spatial coincidence. The current sound is sometimes related to a visual signal that has not yet been seen, we consider this situation as well. Our learning algorithm is tested in online adaptation of audio-motor maps. Since audiomotor maps are not reliable at the beginning of the experiment, learning is bootstrapped using temporal coincidence when there is only one aud...
Download Bibtex file
Download PDF
Benjamin Dittes and Christian Goerick,
"Intelligent System Architectures – Comparison by Translation",
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011.
Abstract
Abstract— System architectures are a central element to enable construction of increasingly complex software systems for intelligent artifacts. Scientific discourse about such architectures requires means to compare approaches and identify common directions. In this contribution we put forth the hypothesis that a meaningful comparison is possible only by translation to a common language. We present SYSTEMATICA 2D as such a common language, suit...
Download Bibtex file
Download PDF
Miranda Grahl,
"Focus of Attention on Relevant Multimodal Events",
University Bielefeld, Uni. Bielefeld, 2011.
Abstract
Current artificial systems for active vision do not tackle an autonomous learning of a gaze control that focuses on multimodal aspects of the environment. They are either based on a reactive gaze control or presume defined models for visual and auditory input in order to attend to objects. However, it is well known in infancy research that infants do not rely on such predefined models (Spelke, 1981). They rather flexibly learn audiovisual associa...
Download Bibtex file
Per Mail Request
Manuel Mühlig, Michael Gienger, Jochen Steil,
"Interactive imitation learning of object movement skills",
Autonomous Robots, vol. 28, no. 1, pp. 1-18, 2011.
Abstract
In this paper we present a new robot control and learning system that allows a humanoid robot to extend its movement repertoire by learning from a human tutor. The focus is learning and imitating motor skills to move and position objects. We concentrate on two major aspects. First, the presented teaching and imitation scenario is fully interactive. A human tutor can teach the robot which is in turn able to integrate newly learned skills into diff...
Download Bibtex file
Download PDF
Stephan Kirstein and Heiko Wersing,
"A Biologically Inspired Approach for Interactive Learning of Categories",
International Conference on Development and Learning, 2011.
Download Bibtex file
Download PDF
Hisashi Sugiura, Michael Gienger, Herbert Janßen, Christian Goerick,
"Reactive Self Collision Avoidance with Dynamic Task Prioritization for Humanoid Robots",
International Journal of Humanoid Robotics (IJHR), vol. 7, no. 1, pp. 31-54, 2010.
Abstract
We propose a self collision avoidance system for humanoid robots designed for interacting with the real world. It protects not only the humanoid robots’ hardware but also expands its working range while keeping smooth motions. It runs in real-time in order to handle unpredictable reactive tasks such as reaching to moving targets tracked by vision during dynamic motions like e.g. biped walking. The collision avoidance is composed of two importan...
Download Bibtex file
Download PDF
Benjamin Inden, Yaochu Jin, Robert Haschke, Helge Ritter,
"NEATfields: Evolution of neural fields for visual discrimination and multiple pole balancing tasks",
Genetic and Evolutionary Computation Conference, 2010.
Download Bibtex file
Download PDF
Samuel John, Heiko Wersing, Helge Ritter,
"An iterative approach to local-PCA",
Proc. International Conference on Artificial Neural Networks ICANN, 2010.
Download Bibtex file
Download PDF
Stephan Kirstein,
"Interactive and life-long learning for identification and categorization tasks",
Honda Research Institute / TU Ilmenau, 2010.
Abstract
The presented thesis focuses on life-long and interactive learning for identification and categorization tasks. The fundamental and still largely unsolved problem of life-long learning with artificial neural networks is the so-called “stability-plasticity dilemma”. To achieve plasticity the learning approach must be able to continuously integrate newly acquired knowledge into its internal representation, while for the stability the conservati...
Download Bibtex file
Per Mail Request
1 ...
93 94 95 96
97 98 ...
151
