Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Learning robot actions based on self-organising language memory.

Stefan Wermter1, Mark Elshaw

  • 1Centre for Hybrid Intelligent Systems, School of Computing and Technology, University of Sunderland, St Peter's Way, Sunderland, SR6 0DD, United Kingdom. stefan.wermter@sunderland.ac.uk

Neural Networks : the Official Journal of the International Neural Network Society
|July 10, 2003
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Will multimodal large language models ever achieve deep understanding of the world?

Frontiers in systems neuroscience·2025
Same author

Disentanglement of Prosody Representations via Diffusion Models and Scheduled Gradient Reversal.

IEEE transactions on neural networks and learning systems·2025
Same author

Pain recognition and pain empathy from a human-centered AI perspective.

iScience·2024
Same author

Map-based experience replay: a memory-efficient solution to catastrophic forgetting in reinforcement learning.

Frontiers in neurorobotics·2023
Same author

A Trained Humanoid Robot can Perform Human-Like Crossmodal Social Attention and Conflict Resolution.

International journal of social robotics·2023
Same author

Emphasizing unseen words: New vocabulary acquisition for end-to-end speech recognition.

Neural networks : the official journal of the International Neural Network Society·2023
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study explores how neural networks can enable robots to understand action instructions using language. The MirrorBot project demonstrates a self-organizing memory system for life-like robotic perception and control.

Area of Science:

  • Robotics and Artificial Intelligence
  • Computational Neuroscience
  • Cognitive Science

Background:

  • Current robot control systems often lack language processing and neural learning capabilities.
  • Understanding how semantic representations emerge in artificial systems is a key challenge.
  • Mirror neurons and cortical assemblies offer insights into biological perception and action representation.

Purpose of the Study:

  • To investigate the emergence of semantic representations of actions in a neural robot.
  • To test the hypothesis that a neural model can produce a life-like perception system for actions.
  • To model action instructions within a self-organizing memory system for robot control.

Main Methods:

  • Utilizing models of cortical assemblies and mirror neurons within the MirrorBot project.

Related Experiment Videos

  • Developing a self-organizing memory model that clusters actions based on associated body parts.
  • Employing actual sensor readings from the MIRA robot to represent semantic features of action verbs.
  • Outlining a hierarchical computational model for a self-organizing robot action control system.

    • Main Results:

    • Demonstrated a self-organizing memory system capable of clustering actions.
    • Successfully used sensor data to represent semantic features of action verbs.
    • Presented a computational model for language-instructed robot control.
    • The neural model shows potential for life-like action perception.

    Conclusions:

    • A self-organizing neural model can effectively process language instructions for robot actions.
    • The approach integrates language, self-organization, and neural assembly concepts for advanced robot control.
    • This work advances the development of robots with more natural and intuitive interaction capabilities.