Search our Publications
Latest Publications
Claudius Gläser, Frank Joublin, Christian Goerick , "Learning and Use of Sensorimotor Schemata Maps", Proceedings of the IEEE 8th International Conference on Development and Learning (ICDL), pp. 1–8, 2009.
AbstractIn this paper we present a framework for the learning and use of sensorimotor schemata. Therefore, we introduce the concept of a schema as a compact representation of an attractor dynamic and discuss how schemata, if embedded into the proposed architecture, can be used to produce, simulate, or recognize goal-directed behaviors. We further present a first implementation of the framework which incorporates well-founded biological principles. Firstl...
Download Bibtex file Download PDF
Nghia Le Minh, Yew-Soon Ong, Yaochu Jin, Bernhard Sendhoff , "Lamarkian memetic algorithms: Local optimum and connectivity structure analysis", Memetic Computing, 2009.
Download Bibtex file Download PDF
Kathrin Lohan, Anna-Lisa Vollmer, Jannik Fritsch, Britta Wrede, Katharina Rohlfing , "How do Modification in Actions Develop with Children's Age and their Increasing Linguistic Abilities?", Cognitive Development, 2009.
Download Bibtex file Download PDF
Behzad Dariush, Michael Gienger, Arjun Arumbakkam, Youding Zhu, Bing Jian, Kikuo Fujimura, Christian Goerick , "Online transfer of human motion to humanoids", International Journal of Humanoid Robotics (IJHR), vol. Vol. 6, no. No. 2, 2009.
AbstractTransferring motion from a human demonstrator to a humanoid robot is an important step toward developing robots that are easily programmable and that can replicate or learn from observed human motion. The so called motion retargeting problem has been well studied and several off-line solutions exist based on optimization approaches that rely on pre-recorded human motion data collected from a marker-based motion capture system. From the perspectiv...
Download Bibtex file Download PDF
Miguel Vaz, Holger Brandl, Frank Joublin, Christian Goerick , "Speech imitation with a child's voice: addressing the correspondence problem", Proceedings of 13th International Conference on Speech and Computer, 2009.
AbstractWe hereby present our first steps towards linking an embodied speech acquisition system and a speech production module, in order to provide a robot with the ability to reproduce acquired speech representations. Due to the type of interaction intended for the robot, we endowed it with a child-like voice, concretized with the use of a new vocoder-like technique for speech synthesis. The task in hand consists of finding and using a correspondence be...
Download Bibtex file Download PDF
Yaochu Jin and Bernhard Sendhoff , "A systems approach to evolutionary multi-objective structural optimization and beyond", IEEE Computational Intelligence Magazine, vol. 4, no. 3, pp. 62–76, 2009.
Download Bibtex file Download PDF
Honglian Guo, Yan Meng, Yaochu Jin , "Self-adaptive multi-robot construction using gene regulatory networks", IEEE Symposium on Artificial Life (IEEE ALIFE 2009), pp. 53–60, 2009.
Download Bibtex file Download PDF
Sven Rebhan, Andreas Richter, Julian Eggert , "Demand-Driven Visual Information Acquisition", Proceedings of the 7th International Conference on Computer Vision Systems (ICVS), pp. 124–133, 2009.
AbstractFast, reliable and demand-driven acquisition of visual information is the key to represent visual scenes efficiently. To achieve this efficiency, a cognitive vision system must plan the utilization of its processing resources to acquire only information relevant for the task. Here, the incorporation of long-term knowledge plays a major role on deciding which information to gather. In this paper, we present a first approach to make use of the know...
Download Bibtex file Download PDF
Martin Ernst Heckmann, Holger Brandl, Jens Schmüdderich, Xavier Domont, Bram Bolder, Inna Mikhailova, Herbert Janßen, Michael Gienger, Achim Bendig, Tobias Rodemann, Mark Dunn, Frank Joublin, Christian Goerick , "Teaching a Humanoid Robot: Headset-Free Speech Interaction for Audio-Visual Association Learning", Proceedings of the 18th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), 2009.
AbstractBased on inspirations from infant development we present a system which learns associations between acoustic labels and visual representations in interaction with its tutor. The system is integrated with a humanoid robot. Except for a few trigger phrases to start learning all acoustical representations are learned online and in interaction. Similar, for the visual domain the clusters are not predefined and fully learned online. In contrast to oth...
Download Bibtex file Download PDF
Volker Willert and Julian Eggert , "A Stochastic Dynamical System for Optical Flow Estimation", IEEE International Conference on Computer Vision (ICCV), 4th International Workshop on Dynamical Vision, 2009.
AbstractSo far, the research on optical flow has mainly concentrated on motion estimations using the observation of a small number of temporal consecutive frames of an image sequence. The dynamics of the flow field evolution is mostly neglected. Our main concern is to stress that visual motion is a dynamic feature of an image input stream and the more visual data has been observed the more precise and detailed we can estimate and predict the motion conta...
Download Bibtex file Download PDF
1 ... 139 140 141 142 143 144 ... 183
Follow us
