Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding

Abstract

In 1994, Karl Sims’ evolved virtual creatures showed the potential of evolutionary algorithms to produce natural, complex morphologies and behaviors [30]. One might assume that nearly 20 years of improvements in computational speed and evolutionary algorithms would produce far more impressive organisms, yet the creatures evolved in the field of artificial life today are not obviously more complex, natural, or intelligent. Fig. 2 demonstrates an example of similar complexity in robots evolved 17 years apart.

BibTeX

@article{cheney2014unshackling,
  year = {2014},
  author = {Cheney, Nick and MacCurdy, Robert and Clune, Jeff and Lipson, Hod},
  title = {Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding},
  journal = {ACM SIGEVOlution},
  publisher = {ACM},
  volume = {7},
  number = {1},
  pages = {11--23},
  doi = {10.1145/2661735.2661737},
}