A Perceptual Memory System for Affordance Learning in Humanoid Robots

  • Marc Kammer
  • Marko Tscherepanow
  • Thomas Schack
  • Yukie Nagai
Conference paper

DOI: 10.1007/978-3-642-21738-8_45

Part of the Lecture Notes in Computer Science book series (LNCS, volume 6792)
Cite this paper as:
Kammer M., Tscherepanow M., Schack T., Nagai Y. (2011) A Perceptual Memory System for Affordance Learning in Humanoid Robots. In: Honkela T., Duch W., Girolami M., Kaski S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2011. ICANN 2011. Lecture Notes in Computer Science, vol 6792. Springer, Berlin, Heidelberg

Abstract

Memory constitutes an essential cognitive capability of humans and animals. It allows them to act in very complex, non-stationary environments. In this paper, we propose a perceptual memory system, which is intended to be applied on a humanoid robot learning affordances. According to the properties of biological memory systems, it has been designed in such a way as to enable life-long learning without catastrophic forgetting. Based on clustering sensory information, a symbolic representation is derived automatically. In contrast to alternative approaches, our memory system does not rely on pre-trained models and works completely unsupervised.

Keywords

Cognitive robotics artificial memory life-long learning affordances 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Marc Kammer
    • 1
    • 2
  • Marko Tscherepanow
    • 1
    • 2
  • Thomas Schack
    • 1
    • 3
  • Yukie Nagai
    • 1
    • 4
  1. 1.CITEC, Cognitive Interaction Technology, Center of ExcellenceBielefeld UniversityBielefeldGermany
  2. 2.Applied Informatics, Faculty of TechnologyBielefeld UniversityBielefeldGermany
  3. 3.Neurocognition and Action, Faculty of Psychology and Sport SciencesBielefeld UniversityBielefeldGermany
  4. 4.Graduate School of EngineeringOsaka UniversitySuita OsakaJapan

Personalised recommendations