Jörg A. Walter

Learn More
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(More)
Robotics deals with the control of actuators using various types of sensors and control schemes. The availability of precise sensorimotor mappings – able to transform between various involved motor, joint, sensor, and physical spaces – is a crucial issue. These mappings are often highly non-linear and sometimes hard to derive analytically. Consequently,(More)
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 <i>Hyperbolic Multi-Dimensional Scaling</i> (H-MDS) extends earlier work [7] using hyperbolic spaces for visualization of tree structures data ( "hyperbolic tree browser" ).By borrowing(More)
Search in and presentation of multimedia collections is an important and complex task. Often it involves various search strategies and the visualization of found object collections. Technically, search strategies can be formulated using distance measures between object pairs. In this paper we propose the use of a projection based method to dynamically(More)
We report on SORMA, the Service Object Request Management Architecture, its concept, developement, and implementation examples. SORMA provides an intelligent “object-bus” for distributed computing and inter-operation of robotics hardware. It is a software framework for rapid development of object-oriented software modules and their integration into(More)
OBJECTIVE Benchmarking and early detection of unfavourable trends. METHODS We implemented a dedicated project-orientated data warehouse, which continuously supplies data for on-line computing of the variable live-adjusted displays (VLADs). To calculate the expected cumulative mortality, we used the multi-variate logistic regression model of the EuroSCORE(More)
We report on two new improvements for the “Parameterised Self-Organizing Map” (PSOM). Both achieve a significant increase in mapping accuracy and computational efficiency. For a growing number of training points the use of higher order polynomials to construct the PSOM “mapping manifold” in [7] can suffer from the increasing tendency to oscillate between(More)
Tactile sensor systems are an essential prerequisite for the implementation of complex manipulation and exploration tasks using robots. Tactile exploration has not yet found its way into many laboratories, because most tactile sensors are technically demanding and expensive. The desire to perform real-time control and pattern recognition with tactile(More)