Publications


MixItUp Demo - Toggle Filtering AND Logic



Why morphology matters

The horizons of evolutionary robotics, , 125-152, 2014


Status: Published

Citations:

Cite: [bibtex]


My Image

Abstract: One can distinguish between traditional and evolutionary robotics (ER) by the way in which each community generates controllers: traditional roboticists hand-design or use learning methods to create control policies, while evolutionary roboticists employ evolutionary algorithms. What further distinguishes these two approaches is that evolutionary algorithms may also be used to optimize robot morphology as well as the control policy. This chapter traces the history of this practice and outlines how we as a community are transitioning from questions regarding how to evolve morphology to why one should do so. Here I outline seven such reasons: selecting or evolving an appropriate morphology can (1) simplify control, (2) make seemingly difficult tasks easier, (3) increase evolvability, (4) provide new behaviors, (5) facilitate the extraction of information from the environment, (6) generate new research questions, and (7) improve scalability.



[edit database entry]
Stacks Image 525289
(null)

  • Stacks Image 525371
    (null)
  • Stacks Image 525379
    (null)
  • Stacks Image 525375
    (null)


Stacks Image 525306
(null)

  • Stacks Image 525319
    (null)
  • Stacks Image 525314
    (null)
  • Stacks Image 525310
    (null)


Stacks Image 525327
(null)

  • Stacks Image 525331
    (null)
  • Stacks Image 525335
    (null)
  • Stacks Image 525339
    (null)


Stacks Image 525346
(null)

  • Stacks Image 525350
    (null)
  • Stacks Image 525354
    (null)
  • Stacks Image 525358
    (null)


Stacks Image 525386
(null)

  • Stacks Image 525390
    (null)
  • Stacks Image 525394
    (null)
  • Stacks Image 525398
    (null)