Alexander Denecke, Heiko Wersing, Jochen Steil, Edgar Körner , "Online Figure-Ground Segmentation with Adaptive Metrics in Generalized LVQ", Neurocomputing, vol. 72, no. 7-9, pp. 1470-1482, 2009.
AbstractWe address the problem of fast figure-ground segmentation of single objects from cluttered backgrounds to improve object learning and recognition. For the segmentation, we use an initial foreground hypothesis to train a classifier for figure and ground on topographically ordered feature maps with Generalized Learning Vector Quantization. We investigate the contribution of several adaptive metrics to enable generalization to the main object parts ...
Björn Schölling , "Binaural Signal Processing", Technische Universität Darmstadt, 2009.
AbstractThe processing and analysis of audio signals play an important role in the interaction of humans and robots. Crucial for the performance of such methods, e.g. speech recognition and source localization, is that the signal of interest is dominant in comparison to the other perceived audio signals. Interfering speech signals, noise, and echoes (reverbera- tion) lead to a severe degradation in performance, and methods that are able to filter the des...
Hisashi Sugiura, Herbert Janßen, Christian Goerick , "Instant prediction for reactive motions with planning. ", 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems , 2009.
AbstractReactive control and planning are complementary methods in robot motion control. The advantage of planning is the ability to find difficult solutions, optimize trajectories globally and not getting stuck in local minima but at higher computational cost. On the other hand, reactive control can handle dynamic or uncertain environments at low computa- tional cost, but may get stuck in local minima. In this paper, we propose a new approach to ...
Bernhard Sendhoff, Edgar Körner, Olaf Sporns , "Creating Brain-like Intelligence", Creating Brain-like Intelligence, pp. 1–15, 2008.
Claudius Gläser, Martin Ernst Heckmann, Frank Joublin, Christian Goerick , "Auditory-based Formant Estimation in Noise using a Probabilistic Framework", Proceedings of the INTERSPEECH, pp. 2606–2609, 2008.
AbstractWe recently introduced a computationally efficient framework for tracking formants which combines a biologically inspired preprocessing for enhancing formants in spectrograms with a probabilistic framework for estimating formant trajectories. In contrast to previously published approaches our tracking scheme relies on the joint distribution of formants rather than using independent tracking instances for each formant separately. Therewith more pr...
Yaochu Jin, Lisa Schramm, Bernhard Sendhoff , "A Gene Regulatory Model for the Development of Primitive Nervous Systems", INNS-NNN Symposia on Modeling the Brain and Nervous Systems, 2008.
Imran Bashir Bhatti , "Autonomous learning in intelligent vehicles", TU Darmstadt, 2008.
AbstractAutonomous systems, i.e., intelligent vehicles and robots use machine learning techniques to classify or recognise the identity of an object. The object identification aids them to make intelligent decisions in different situations. Research on classification techniques shows that classification techniques are not always accurate and reliable. In this thesis we apply a newly proposed concept termed ”cross-module learning” for cognitive system des...
Ben Jones, Yaochu Jin, Xin Yao, Bernhard Sendhoff , "Evolution of Neural Organization in A Hydra-Like Animat", International Conference on Neural Information Processing of the Asia-Pacific Neural Network Assembly (ICONIP-2008), 2008.
Michael Gienger, Mark Toussaint, Nikolai Jetchev, Achim Bendig, Christian Goerick , "Optimization of fluent approach and grasp motions", International Conference on Humanoid Robots, 2008.
AbstractGenerating a fluent motion of approaching, grasping and lifting an object comprises a number of problems which are typically tackled separately. Some existing research specializes on the optimization of the final grasp posture based on force closure criteria neglecting the motion necessary to approach this grasp. Other research specializes on motion optimization including collision avoidance criteria, but typically not considering the subsequent ...
Bram Bolder, Holger Brandl, Martin Heracles, Herbert Janßen, Inna Mikhailova, Jens Schmüdderich, Christian Goerick , "Expectation-driven Autonomous Learning and Interaction System", IEEE-RAS International Conference on Humanoid Robots, 2008.
AbstractWe introduce our latest autonomous learning and interaction system instance ALIS 2. It comprises different sensing modalities for visual (depth blobs, planar surfaces, motion) and auditory (speech, localization) signals and self-collision free behavior generation on the robot ASIMO. The system design emphasizes the split into a completely autonomous reactive layer and an expectation generation layer. Different feature channels can be classied and...