One-shot path planning for multi-agent systems using fully convolutional neural network

no code implementations • 1 Apr 2020 • Tomas Kulvicius, Sebastian Herzog, Timo Lüddecke, Minija Tamosiunaite, Florentin Wörgötter

In contrast to that, we propose a novel method by utilising fully convolutional neural network, which allows generation of complete paths, even for more than one agent, in one-shot, i. e., with a single prediction step.

Generation of Paths in a Maze using a Deep Network without Learning

no code implementations • 1 Apr 2020 • Tomas Kulvicius, Sebastian Herzog, Minija Tamosiunaite, Florentin Wörgötter

Trajectory- or path-planning is a fundamental issue in a wide variety of applications.

Transfer entropy-based feedback improves performance in artificial neural networks

no code implementations • 13 Jun 2017 • Sebastian Herzog, Christian Tetzlaff, Florentin Wörgötter

The structure of the majority of modern deep neural networks is characterized by uni- directional feed-forward connectivity across a very large number of layers.