Learning robot actions based on self-organising language memory

Stefan Wermter, Mark Elshaw

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)

Abstract

In the MirrorBot project we examine perceptual processes using models of cortical assemblies and mirror neurons to explore the
emergence of semantic representations of actions, percepts and concepts in a neural robot. The hypothesis under investigation is whether a neural model will produce a life-like perception system for actions. In this context we focus in this paper on how instructions for actions can be modeled in a self-organising memory. Current approaches for robot control often do not use language and ignore neural learning. However, our approach uses language instruction and draws from the concepts of regional distributed modularity, self-organisation and neural assemblies. We describe a self-organising model that clusters actions into different locations depending on the body part they are
associated with. In particular, we use actual sensor readings from the MIRA robot to represent semantic features of the action verbs.
Original languageEnglish
Pages (from-to)691-699
Number of pages9
JournalNeural Networks
Volume16
Issue number5-6
DOIs
Publication statusPublished - 2003
Externally publishedYes

Keywords

  • Mirror neurons
  • Robot
  • Language Memory

Fingerprint Dive into the research topics of 'Learning robot actions based on self-organising language memory'. Together they form a unique fingerprint.

Cite this