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

Evolutionary neurocontrollers for autonomous mobile robots.

D Floreano1, F Mondada

  • 1Laboratory of Microcomputing (LAMI), Swiss Federal Institute of Technology (EPFL), CH-1015, Lausanne, Switzerland

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
PubMed
Summary

This study presents a method for autonomously evolving robot controllers, demonstrating how different environments and robot designs shape behavior and neural mechanisms for adaptive robotics.

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 data-driven method for reconstructing and modelling social interactions in moving animal groups.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2020
Same author

Bioinspired morphing wings for extended flight envelope and roll control of small drones.

Interface focus·2017
Same author

Sleep and Wake Classification With ECG and Respiratory Effort Signals.

IEEE transactions on biomedical circuits and systems·2013
Same author

Social integration of robots into groups of cockroaches to control self-organized choices.

Science (New York, N.Y.)·2007
Same author

Evolution of adaptive synapses: robots with fast adaptive behavior in new environments.

Evolutionary computation·2001
Same author

Evolutionary robots with on-line self-organization and behavioral fitness.

Neural networks : the official journal of the International Neural Network Society·2000

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Computational Neuroscience

Background:

  • Autonomous mobile robots require sophisticated control systems.
  • Evolving robot controllers without human intervention is a key challenge in adaptive robotics.

Purpose of the Study:

  • To present a unified methodology for evolving neurocontrollers of autonomous mobile robots.
  • To analyze the impact of environmental variations and robot morphologies on evolved behaviors and neural mechanisms.

Main Methods:

  • Describing principles for building mobile robots and tools for adaptive robotics experiments.
  • Overviewing different approaches to evolutionary robotics.
  • Presenting a novel methodology for neurocontroller evolution.

Related Experiment Videos

Main Results:

  • Different environments shape distinct behaviors and neural mechanisms under similar selection criteria.
  • Incremental evolution in changing environments and morphologies leads to adaptation.
  • Evolved plastic neurocontrollers exhibit dynamic stability through continuously changing synapses.

Conclusions:

  • The methodology offers a unified approach to evolutionary robotics.
  • Evolved neurocontrollers have implications for engineering, biology, cognitive science, and artificial life.
  • Future research directions include further exploration of plastic neurocontrollers and their applications.