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 Video

Updated: May 29, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Learning slow features with reservoir computing for biologically-inspired robot localization.

Eric Antonelo1, Benjamin Schrauwen

  • 1Department of Electronics and Information Systems, Ghent University, Ghent, Belgium. eric.antonelo@elis.ugent.be

Neural Networks : the Official Journal of the International Neural Network Society
|September 28, 2011
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

Oncilla Robot: A Versatile Open-Source Quadruped Research Robot With Compliant Pantograph Legs.

Frontiers in robotics and AI·2021
Same author

On learning navigation behaviors for small mobile robots with reservoir computing architectures.

IEEE transactions on neural networks and learning systems·2015
Same author

Memristor models for machine learning.

Neural computation·2015
Same author

True zero-training brain-computer interfacing--an online study.

PloS one·2014
Same author

Design and control of compliant tensegrity robots through simulation and hardware validation.

Journal of the Royal Society, Interface·2014
Same author

Integrating dynamic stopping, transfer learning and language models in an adaptive zero-training ERP speller.

Journal of neural engineering·2014
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

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

New results on prescribed-time synchronization of complex networks via intermittent control.

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

Variance-constrained multi-view ensemble broad network for imbalanced data.

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

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

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

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

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

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

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

This study introduces a novel biologically-inspired AI architecture for robots to learn spatial environments using only distance sensors. The system successfully predicts robot locations without odometry, mimicking hippocampal place cells.

Area of Science:

  • Robotics
  • Computational Neuroscience
  • Artificial Intelligence

Background:

  • Robots often rely on odometry for spatial representation, which can be inaccurate.
  • Unsupervised learning of spatial environments from limited sensor data remains a challenge.
  • Biologically-inspired models offer potential for robust spatial learning.

Purpose of the Study:

  • To propose a hierarchical, biologically-inspired architecture for unsupervised, sensor-based spatial representation learning in robots.
  • To investigate the role of a recurrent neural network reservoir and feature extraction methods (SFA, ICA) in spatial learning.
  • To demonstrate the system's ability to predict robot location using only noisy, short-range distance sensors.

Main Methods:

  • A three-layer hierarchical architecture: a fixed recurrent neural network (reservoir), Slow Feature Analysis (SFA), and Independent Component Analysis (ICA).

Related Experiment Videos

Last Updated: May 29, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

  • The reservoir projects sensor input into a high-dimensional dynamic space.
  • SFA extracts slowly-varying signals, and ICA learns sparse coding for place selectivity.

    • Main Results:

    • The ICA layer exhibits high place selectivity, analogous to hippocampal place cells.
    • The system accurately predicts robot locations in simulated and real environments without odometry.
    • The reservoir layer is crucial for learning spatial representations from low-dimensional, noisy sensor inputs due to its fading memory.

    Conclusions:

    • The proposed biologically-inspired architecture effectively learns spatial representations from limited sensor data.
    • The system's ability to predict location without odometry highlights its potential for robust robot navigation.
    • The reservoir's memory mechanism is key to overcoming sensor ambiguity and enabling accurate localization.