Using robots to investigate the evolution of adaptive behavior

  title={Using robots to investigate the evolution of adaptive behavior},
  author={J. Bongard},
  journal={Current Opinion in Behavioral Sciences},
  • J. Bongard
  • Published 2015
  • Computer Science
  • Current Opinion in Behavioral Sciences
  • In the field of evolutionary robotics, investigators evolve populations of autonomous machines to exhibit some desired behavior. The neurology, morphology, or both may be placed under evolutionary control, and different behaviors can be selected for. Results from this approach can generate unique and surprising hypotheses about why certain behaviors evolve, regardless of whether they emerge in organisms or machines. To illustrate this approach, I describe recent work on the evolution of… CONTINUE READING
    Self-Organized Behavior Generation for Musculoskeletal Robots
    • 6
    • PDF
    Modularity and Sparsity: Evolution of Neural Net Controllers in Physically Embodied Robots
    • 4
    • PDF
    Self-organized control for musculoskeletal robots
    • 2
    • PDF
    The world as its own best controller: a case study with anthropomimetic robots
    • 1
    • PDF
    Towards Adversarial Training for Mobile Robots
    Situation Awareness for Proactive Robots in HRI
    • 1


    Publications referenced by this paper.
    Explorations in Evolutionary Robotics
    • 439
    • PDF
    Evolved Machines Shed Light on Robustness and Resilience
    • 21
    • PDF
    Grand Challenges for Evolutionary Robotics
    • 38
    • PDF
    Environmental Influence on the Evolution of Morphological Complexity in Machines
    • 86
    • PDF
    Challenges in evolving controllers for physical robots
    • 275
    From evolutionary computation to the evolution of things
    • 210
    • PDF