We propose the combination of two recently introduced methods for the interactive visual data mining of large collections of data. Both hyperbolic multidimensional scaling (HMDS) and hyperbolic self-organizing maps (HSOM) employ the extraordinary advantages of the hyperbolic plane (H2): (i) the underlying space grows exponentially with its radius around each point deal for embedding high-dimensional (or hierarchical) data; (ii) the Poincare model of the IH/sup 2/ exhibits a fish-eye perspective with a focus area and a context preserving surrounding; (in) the mouse binding of focus-transfer allows intuitive interactive navigation. The HMDS approach extends multidimensional scaling and generates a spatial embedding of the data representing their dissimilarity structure as faithfully as possible. It is very suitable for interactive browsing of data object collections, but calls for batch precomputation for larger collection sizes. The HSOM is an extension of Kohonen's self-organizing map and generates a partitioning of the data collection assigned to an IH/sup 2/ tessellating grid. While the algorithm's complexity is linear in the collection size, the data browsing is rigidly bound to the underlying grid. By integrating the two approaches, we gain the synergetic effect of adding advantages of both. And the hybrid architecture uses consistently the IH/sup 2/ visualization and navigation concept. We present the successfully application to a text mining example involving the Reuters-21578 text corpus.

We propose a novel projection based visualization method for high-dimensional datasets by combining concepts from MDS and the geometry of the hyperbolic spaces. Our approach Hyperbolic Multi-Dimensional Scaling (H-MDS) extends earlier work [7] using hyperbolic spaces for visualization of tree structures data ( "hyperbolic tree browser" ).By borrowing concepts from multi-dimensional scaling we map proximity data directly into the 2-dimensional hyperbolic space (H2). This removes the restriction to "quasihierarchical", graph-based data -- limiting previous work. Since a suitable distance function can convert all kinds of data to proximity (or distance-based) data this type of data can be considered the most general.We used the circular Poincaré model of the H2 which allows effective human-computer interaction: by moving the "focus" via mouse the user can navigate in the data without loosing the "context". In H2 the "fish-eye" behavior originates not simply by a non-linear view transformation but rather by extraordinary, non-Euclidean properties of the H2. Especially, the exponential growth of length and area of the underlying space makes the H2 a prime target for mapping hierarchical and (now also) high-dimensional data.We present several high-dimensional mapping examples including synthetic and real world data and a successful application for unstructured text. By analyzing and integrating multiple film critiques from news:rec.art.movies.reviews and the internet movie database, each movie becomes placed within the H2. Here the idea is, that related films share more words in their reviews than unrelated. Their semantic proximity leads to a closer arrangement. The result is a kind of high-level content structured display allowing the user to explore the "space of movies".

We present a system for learning the 3 DOF fine-positioning task of a robot manipulator (Puma 260) using a gripper mounted camera. Small lateral gripper-target misalignments are corrected in one step. Larger ones employ a previous coarse adjustment move in order to bound the parallax effects of the close camera focus. We build object specialized, neural network-based pose estimators with a rather small set of Gabor filters. Gabor filters perform a spatially localized frequency analysis and resemble the spatial response profile of receptive fields found in visual cortex neurons. The system demonstrates efficiency w.r.t. speed and accuracy, as well as robustness against changing illumination and object conditions.

A system for learning the pre-grasp positioning task for a robot manipulator is presented. The images delivered from a gripper mounted camera are analysed using Gabor filters which resemble the spatial response profiles of receptive fields found in visual cortex neurons. Using a quite small feature set, the system demonstrated efficiency with respect to speed and accuracy, as well as robustness against changing light conditions. Furthermore, we compare it to two other approaches, aiming at the same goal: an appearance-based PCA fuzzy control and a PSOM based Hough-Transform system.

We discuss the "parametrized self-organizing maps" (PSOM) as a learning method for rapidly creating high-dimensional, continuous mappings. By making use of available topological information the PSOM shows excellent generalization capabilities from a small set of training data. The PSOM provides, as an important generalization, a flexibly usable continuous associate memory. Task specifications for redundant manipulators often leave the problem of picking one action from a subspace of possible alternatives. The PSOM approach offers a flexible and compact form to select various constraint and target functions previously associated. We present application results for learning several kinematic relations of a hydraulic robot finger in a single PSOM module. Based on only 27 data points, the PSOM learns the inverse kinematic with a mean positioning accuracy of 1% of the entire workspace. Also, the PSOM learns various ways to resolve the redundancy problem for positioning a 4-DOF manipulator.

In this paper an approach is presented for thehierarchical verification of the memory control units, I/O adaptersand processor interconnect units as found in multiprocessorcomputer systems. It is shown how such units could be verifiedbetter and faster by the introduction of random executable timingdiagrams and associated CAD tool support. Furthermore, itis shown how the timing diagrams for the unit network verificationare easily derived from the timing diagrams specified for theunits. The multiprocessor hardware test showed the effectivenessof the proposed verification approach.

Tactile sensor systems are an essential prerequisite for the implementation of complex manipulation and exploration tasks using robots. The desire to perform real-time control and pattern recognition with tactile sensors led us to the design of a cost-effective artificial fingertip. At our laboratory two distinct types of sensors are in use: force/position sensors and slippage detectors. We report on first experimental results with a fingertip prototype performing rolling and sliding movements over a flat surface. To facilitate experimentation with tactile sensors, we designed and developed a data acquisition and transportation system that fulfils our demands on bandwidth, flexibility, and cost. This system consists of two hardware components, a configurable multichannel analog signal sampler to acquire sensor data, and an intelligent dual-ported random-access buffer to avoid data transportation bottlenecks.

This paper introduces the Service Object Request Management Architecture (SORMA), its design issues, and its concepts. It is a software framework for rapid development of object-oriented software modules and their integration into stand-alone and distributed applications. SORMA provides an intelligent "object-bus" for interoperating and sharing distributed computing and robotics hardware. We investigate the question of why too many valuable hardware and software systems and components are a "one-of-a-kind" product which do not find economical re-use. We analyze the "costs of communication" between the component's builder and all its users, who build solutions. We propose to pay much more attention to interactive exploration frameworks, which support rapid, qualified information gain on context-situated, efficient applicability. SORMA demonstrates how to reach self-explaining, built-in interactivity which does not impair the component's real-time efficiency.

The implementation of two neural network algorithms for visuo-motor control of an industrial robot (Puma 562) is reported. The first algorithm uses a vector quantization technique, the ;neural-gas' network, together with an error correction scheme based on a Widrow-Hoff-type learning rule. The second algorithm employs an extended self-organizing feature map algorithm. Based on visual information provided by two cameras, the robot learns to position its end effector without an external teacher. Within only 3000 training steps, the robot-camera system is capable of reducing the positioning error of the robot's end effector to approximately 0.1% of the linear dimension of the work space. By employing adaptive feedback the robot succeeds in compensating not only slow calibration drifts, but also sudden changes in its geometry. Hardware aspects of the robot-camera system are discussed.

The problem of predicting highly nonlinear time sequence data, where the usual approach using adaptive linear regressive models encounters difficulty, is considered. For this case, the use of an adaptive covering of the state space of the process with a set of linear regressive models, each of which is only locally used, is suggested. It is shown that such an adaptive covering, together with learning of the appropriate prediction coefficients, can be realized using Kohonen's algorithm of self-organizing maps. To illustrate the method, simulation results for a set of benchmarking problems are given