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 body building: adaptive physical designs for robots.

P Funes1, J Pollack

  • 1Computer Science Department, Volen Center for Complex Systems, Brandeis University, Waltham, MA 02454-9110, USA. pablo@cs.brandeis.edu

Artificial Life
|June 3, 1999
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

Long-term efficacy of NASHA Dx injection therapy for treatment of fecal incontinence.

Neurogastroenterology and motility·2014
Same author

Genotype List String: a grammar for describing HLA and KIR genotyping results in a text string.

Tissue antigens·2013
Same author

Randomized clinical trial of fluid restriction in colorectal surgery.

The British journal of surgery·2011
Same author

The role of blue cross and insurance companies in insuring group practice.

Bulletin of the New York Academy of Medicine·2009
Same author

Late adverse effects of short-course preoperative radiotherapy in rectal cancer.

The British journal of surgery·2006
Same author

Three generations of automatically designed robots.

Artificial life·2001

This study introduces a novel evolutionary approach to design robot bodies by simulating the assembly of components. This method overcomes the "chicken and egg" problem in evolutionary robotics, enabling the creation of physically buildable artificial life forms.

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Evolutionary Computation

Background:

  • Evolutionary robotics faces a "chicken and egg" problem: controlling complex bodies requires pre-existing brains, while building controllable bodies assumes a brain.
  • Coevolution of bodies and brains is gaining traction, but a lack of frameworks hinders physical structure evolution.
  • Simulated evolution often yields unbuildable entities, and real-world embodied evolution is slow.

Purpose of the Study:

  • To address the challenge of body evolution in artificial life.
  • To develop a general framework for the evolution of physical structures in robotics.
  • To enable the creation of physically constructible robot bodies through evolutionary techniques.

Main Methods:

  • Applying evolutionary techniques to design structures from elementary, self-assembling components.

Related Experiment Videos

  • Utilizing a simulator that calculates forces, stresses, and stability for 3D brick structures.
  • Generating schematic assemblies for physical construction.

    • Main Results:

    • Demonstrated a functional approach to robot body building.
    • Successfully evolved diverse and buildable robotic artifacts.
    • Validated the evolutionary design of physical structures.

    Conclusions:

    • The presented method offers a viable solution for evolving physical robot bodies.
    • This approach facilitates the coevolution of robot morphology and control.
    • Enables the creation of novel, physically realized artificial organisms.