Dynamic Neural Fields as Building Blocks of a Cortex-Inspired Architecture for Robotic Scene Representation

  • Based on the concepts of dynamic field theory (DFT), we present an architecture that autonomously generates scene representations by controlling gaze and attention, creating visual objects in the foreground, tracking objects, reading them into working memory, and taking into account their visibility. At the core of this architecture are three-dimensional dynamic neural fields (DNFs) that link feature to spatial information. These three-dimensional fields couple into lower dimensional fields, which provide the links to the sensory surface and to the motor systems. We discuss how DNFs can be used as building blocks for cognitive architectures, characterize the critical bifurcations in DNFs, as well as the possible coupling structures among DNFs. In a series of robotic experiments, we demonstrate how the DNF architecture provides the core functionalities of a scene representation.

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Stephan K. U. Zibner, Faubel Christian, Ioannis Iossifidis, Gregor Schoner
URL:https://ieeexplore.ieee.org/document/5709974
Parent Title (English):IEEE Transactions on Autonomous Mental Development
Document Type:Article
Language:English
Year of Completion:2011
Date of first Publication:2019/02/12
Release Date:2019/02/12
Volume:3
Issue:1
First Page:74
Last Page:91
Institutes:Fachbereich 1 - Institut Informatik
DDC class:600 Technik, Medizin, angewandte Wissenschaften
000 Allgemeines, Informatik, Informationswissenschaft / 004 Informatik
600 Technik, Medizin, angewandte Wissenschaften / 621.3 Elektrotechnik, Elektronik
Licence (German):License LogoNo Creative Commons