Miranda Grahl , "Focus of Attention on Relevant Multimodal Events", University Bielefeld, Uni. Bielefeld, 2011.
AbstractCurrent 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...
Manuel Mühlig, Michael Gienger, Jochen Steil , "Interactive imitation learning of object movement skills", Autonomous Robots, vol. 28, no. 1, pp. 1-18, 2011.
Stephan Kirstein and Heiko Wersing , "A Biologically Inspired Approach for Interactive Learning of Categories", International Conference on Development and Learning, 2011.
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.
AbstractWe 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 important ...
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.
Samuel John, Heiko Wersing, Helge Ritter , "An iterative approach to local-PCA", Proc. International Conference on Artificial Neural Networks ICANN, 2010.
Stephan Kirstein , "Interactive and life-long learning for identification and categorization tasks", Honda Research Institute / TU Ilmenau, 2010.
AbstractThe 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 conservation o...
Jens Schmüdderich , "Multimodal learning of grounded concepts in embodied systems", Bielefeld University, 2010.
AbstractThe research of methods equipping a technical system with the ability to learn mental concepts of objects, properties, or actions is an important step towards the understanding of intelligence. Moreover, for everyday interaction, a system acquiring knowledge by learning is obviously advantageous compared to a system that requires programming. A special challenge arises from the variety of different characteristics whose association forms our unde...
Maha Salem, Stefan Kopp, Ipke Wachsmuth, Frank Joublin , "Generating Multi-Modal Robot Behavior Based on a Virtual Agent Framework", IEEE Int. Conf. on Robotics and Automation (ICAIR/ICRA), 2010.
Honglian Guo, Yan Meng, Yaochu Jin , "Analysis of Local Communication Load in Shape Formation of a Distributed Morphogenetic Swarm Robotic System", IEEE World Congress on Computational Intelligence, 2010.