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

A self-organizing neural network architecture for navigation using optic flow

S Cameron1, S Grossberg, F H Guenther

  • 1Department of Cognitive and Neural Systems, Boston University, MA 02215, USA.

Neural Computation
|February 24, 1998
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

Improving access to postpartum contraception - a review of global guidelines with ESCRH consensus recommendations for Europe.

The European journal of contraception & reproductive health care : the official journal of the European Society of Contraception·2025
Same author

High-resolution measurements of swordfish skin surface roughness.

Bioinspiration & biomimetics·2023
Same author

Mild to moderate increases in activity are associated with increased seizure incidence in dogs with idiopathic epilepsy receiving anti-epileptic drugs.

The Journal of small animal practice·2023
Same author

Effect of an intervention of exercise on sleep and seizure frequency in idiopathic epileptic dogs.

The Journal of small animal practice·2022
Same author

A persistent plaque on the back of the hand.

Clinical and experimental dermatology·2022
Same author

Study protocol P-MAPS: microbiome as predictor of severity in acute pancreatitis-a prospective multicentre translational study.

BMC gastroenterology·2021
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study presents a self-organizing neural network that uses optic flow and eye position to enable reactive navigation. The network learns to represent heading, depth, and object locations for obstacle avoidance and target pursuit.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Robotics

Background:

  • The brain processes optic flow and eye movements for navigation.
  • Developing artificial systems that mimic these biological processes is challenging.

Purpose of the Study:

  • To create a self-organizing neural network architecture for reactive navigation.
  • To transform optic flow and eye position data into representations of heading, scene depth, and object locations.

Main Methods:

  • A novel neural network architecture trained via an action-perception cycle.
  • Utilizing self-generated movements to produce optic flow for unsupervised learning.
  • Employing a self-organizing feature map to categorize flow patterns and code heading directions.

Related Experiment Videos

Main Results:

  • The network successfully generated representations for heading, scene depth, and moving object locations.
  • Simulations demonstrated effective obstacle avoidance and target pursuit capabilities.
  • The network demonstrated robustness with both noise-free and noisy optic flow data.

Conclusions:

  • The proposed architecture offers a biologically plausible mechanism for self-organizing navigation.
  • This approach allows for adaptive tuning without explicit sensor geometry knowledge.
  • The findings contribute to advancements in autonomous navigation systems.