Learn More
— The free and open source Tele-Operation Platform of the MPI for Biological Cybernetics (TeleKyb) is an end-to-end software framework for the development of bilateral teleoperation systems between human interfaces (e.g., haptic force feedback devices or gamepads) and groups of quadrotor Unmanned Aerial Vehicles (UAVs). Among drivers for devices and robots(More)
The contribution describes the application of the Team 'Computational Intelligence Group' from the University of Applied Sciences Mittweida (Germany) to the ICMLA Face Recognition Challenge 2012. In particular we explain the data preprocessing and feature extraction, which was applied before classification learning. Further we give details about the used(More)
In the present paper we investigate the application of differentiable kernel for generalized matrix learning vector quantization as an alternative kernel-based classifier, which additionally provides classification dependent data visualization. We show that the concept of differentiable kernels allows a prototype description in the data space but equipped(More)
In this paper we propose and experimentally validate a bilateral teleoperation framework where a group of UAVs are controlled over an unreliable network with typical intercontinental time delays and packet losses. This setting is meant to represent a realistic and challenging situation for the stability the bilateral closed-loop system. In order to increase(More)
We propose in this contribution a method for l1-regularization in prototype based relevance learning vector quantization (LVQ) for sparse relevance proles. Sparse relevance proles in hyperspectral data analysis fade down those spectral bands which are not necessary for classication. In particular, we consider the sparsity in the relevance prole enforced by(More)