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

Neural network models of bilateral coordination.

D S Farrar1, D Zipser

  • 1Department of Cognitive Science, University of California, San Diego, USA.

Biological Cybernetics
|April 8, 1999
PubMed
Summary

This study presents two arm movement control methods: a motion planner for complex movements and neural networks that efficiently emulate it. The research offers insights into brain systems for bilateral coordination.

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

A model of visual-spatial memory across saccades.

Vision research·2001
Same author

A model of reaching dynamics in primary motor cortex.

Journal of cognitive neuroscience·1998
Same author

Analysis of direction selectivity arising from recurrent cortical interactions.

Neural computation·1998
Same author

A model that accounts for activity in primate frontal cortex during a delayed matching-to-sample task.

The Journal of neuroscience : the official journal of the Society for Neuroscience·1998
Same author

A spiking network model of short-term active memory.

The Journal of neuroscience : the official journal of the Society for Neuroscience·1993
Same author

Identification models of the nervous system.

Neuroscience·1992

Area of Science:

  • Robotics and Artificial Intelligence
  • Computational Neuroscience

Background:

  • Controlling robotic arm movement, especially for noncolliding, goal-directed tasks, is computationally challenging.
  • Existing motion planning algorithms can be resource-intensive.

Purpose of the Study:

  • To describe two distinct mechanisms for controlling a pair of arms.
  • To develop computationally efficient methods for coordinated arm movement.
  • To provide insights into neural mechanisms of bilateral coordination.

Main Methods:

  • An engineered motion planner was developed to solve the problem of noncolliding, goal-directed arm movements.
  • Neural networks were trained to emulate the functional behavior of the motion planner.
  • Computational resource requirements were compared between the two methods.

Main Results:

  • The engineered motion planner successfully generated solutions for complex arm movements.
  • Neural networks effectively emulated the motion planner's coordinated behaviors.
  • The neural network approach demonstrated significantly reduced computational resource demands.

Conclusions:

  • Neural networks offer a computationally efficient alternative for emulating complex motion planning.
  • The study provides a framework for understanding brain systems involved in bilateral coordination.
  • Testable predictions regarding neural response properties in bilateral coordination are proposed.

Related Experiment Videos