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

Evolving mobile robots in simulated and real environments

O Miglino1, H H Lund, S Nolfi

  • 1Department of Psychology, University of Palermo, Italy. orazio@caio.irmkant.rm.cnr.it

Artificial Life
|January 1, 1995
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

Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems.

Neural networks : the official journal of the International Neural Network Society·2003
Same author

[Robotics and artificial intelligence in hospitals].

Ugeskrift for laeger·2002
Same author

Duplication of modules facilitates the evolution of functional specialization.

Artificial life·2000
Same author

Embodied artificial life.

Artificial life·1999
Same author

Coevolving predator and prey robots: do "arms races" arise in artificial evolution?

Artificial life·1999
Same author

Physical and temporal scaling considerations in a robot model of cricket calling song preference.

Artificial life·1998
Same journal

If Turing Played Piano With an Artificial Partner.

Artificial life·2026
Same journal

Discovering Partial Differential Equations With Neural Cellular Automata.

Artificial life·2026
Same journal

Book Review: Exploring the Boundaries of Life-as-It-Is.

Artificial life·2026
Same journal

System 0/1/2/3: Quad-Process Theory for Multitimescale Embodied Collective Cognitive Systems.

Artificial life·2025
Same journal

To Engineer an Angel, First Validate the Devil: Analyzing the "Could Be" in Artificial Life's "Life as-It-Could-Be".

Artificial life·2025
Same journal

Untapped Potential in Self-Optimization of Hopfield Networks: The Creativity of Unsupervised Learning.

Artificial life·2025
See all related articles

This study shows how to effectively train autonomous robots using simulations. By modeling robot dynamics and using noise, researchers can bridge the gap between simulated and real-world performance, enabling robust robotic control systems.

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Machine Learning

Background:

  • Simulation validity is crucial for developing control systems in autonomous robots, especially in evolutionary robotics.
  • Training robots in real environments is possible but often impractical due to the high number of trials required.

Purpose of the Study:

  • To investigate methods for improving the transfer of robot control systems from simulation to the real world.
  • To reduce the performance gap between simulated and real-world robot behaviors.
  • To validate the effectiveness of evolutionary robotics in simulated environments.

Main Methods:

  • Evolving neural controllers for a Khepera robot within computer simulations.
  • Building accurate robot-environment dynamics models by sampling real-world data.

Related Experiment Videos

  • Introducing a conservative noise model to bridge the simulation-reality gap.
  • Continuing the evolutionary process in the real environment for fine-tuning.

    • Main Results:

    • An accurate model of robot-environment dynamics was successfully built.
    • A significant reduction in the performance gap between simulated and real environments was achieved using noise.
    • Continued evolution in the real environment led to robust and successful results.

    Conclusions:

    • Simulation-based training is a viable and efficient method for developing autonomous robot control systems.
    • The proposed methods effectively minimize the challenges of transferring simulated agents to physical robots.
    • Evolutionary robotics combined with simulation and real-world adaptation offers a powerful approach for robust robotic development.