Christian Faubel

About

Christian Faubel is a cognitive robotics researcher whose work sits at the intersection of computational neuroscience, dynamic field theory, and autonomous robotic systems. Best known for his pioneering contributions to neural architectures for real-time object recognition and scene representation, Faubel has spent much of his career exploring how biologically inspired principles can endow robots with human-like perceptual and cognitive capabilities. His most influential work, "Learning to recognize objects on the fly" (2008, 73 citations), demonstrated that robots could acquire and recognize objects dynamically using neurally grounded mechanisms — a significant advance for human-robot collaboration. Building on this foundation, his research into Dynamic Neural Fields (DNF) as architectural building blocks (2011, 41 citations) yielded sophisticated systems capable of attention control, object tracking, and working memory integration within a unified cortex-inspired framework. Faubel also made early and lasting contributions to anthropomorphic robot design through the CORA project (2003–2004), developing a cooperative robotic assistant integrating vision, audition, haptics, and gesture recognition. His later work extended DNF principles into word learning and embodied neural dynamics, reflecting a sustained commitment to grounding symbolic cognition in physical interaction. With nearly 200 cumulative citations, his research continues to inform modern neurodynamic approaches to robotics and cognitive architecture.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning to recognize objects on the fly: A neurally based dynamic field approach

   73 citations · 2008
2. 2
   Dynamic Neural Fields as Building Blocks of a Cortex-Inspired Architecture for Robotic Scene Representation

   41 citations · 2011
3. 3
   Anthropomorphism as a pervasive design concept for a robotic assistant

   25 citations · 2004
4. 4
   CORA: An anthropomorphic robot assistant for human environment

   19 citations · 2003
5. 5
   A neuro-dynamic architecture for one shot learning of objects that uses both bottom-up recognition and top-down prediction

   16 citations · 2009
6. 6
   Making a robotic scene representation accessible to feature and label queries

   7 citations · 2011
7. 7
   Scenes and tracking with dynamic neural fields: How to update a robotic scene representation

   6 citations · 2010
8. 8
   Dynamic Scene Representations and Autonomous Robotics

   6 citations · 2015
9. 9
   Grounding Word Learning in Space and Time

   4 citations · 2015
10. 10
    Embodied Neural Dynamics

    3 citations · 2015

Key Collaborators

Contact & Links