Evolved virtual creatures (1994)

Evolved virtual creatures (1994)

 

First virtual evolution, advanced virtual intelligence

Video

Trivia:

1) Directed by by Carl Sims (Panspermia (1990).   

2) This narrated computer animation shows results from a research project involving simulated Darwinian evolutions of virtual block creatures. A population of several hundred creatures is created within a supercomputer, and each creature is tested for their ability to perform a given task, such the ability to swim in a simulated water environment. The successful survive, and their virtual genes containing coded instructions for their growth, are copied, combined, and mutated to make offspring for a new population. The new creatures are again tested, and some may be improvements on their parents. As this cycle of variation and selection continues, creatures with more and more successful behaviors can emerge.

3) Generated autonomous three-dimensional virtual creatures without requiring cumbersome user specifications, design efforts, or knowledge of algorithmic details. 

4) The creatures shown are results the final products from many independent simulations in which they were selected for swimming, walking, jumping, following, and competing for control of a green cube. 

Results: evolutions were performed for each of  the behavior  selection methods. A  population  of  interbreeding creatures often converges toward homogeneity, but each separately run evolution can produce completely different locomotion strategies that satisfy the requested behavior. For this reason, many separate evolutions were performed, each for 50 to 100 generations, and the most successful

creatures  of each evolution were inspected. A variety of  more complex  strategies  also  emerged  from  some  evolutions.  A  few creatures  pulled  themselves  through  the  water  with  specialized sculling appendages. Some used two symmetrical flippers or even large numbers of similar flippers to propel themselves, and several multi-segmented  watersnake  creatures  evolved  that  wind  through the water with sinusoidal motions, direction of future work might be to adjust the genetic language  of  possible  creatures  to  describe  only  those  that  could actually be built as real robots. The virtual robots that can best perform  a  given  task  in  simulation  would  then  be  assembled,  and would hopefully also perform well in reality. Much work could be done to dress up these virtual creatures to give them different shapes and improved rendered looks. Flexible skin could surround or be controlled by the rigid components. Various materials could be added such as scales, hair, fur, eyes, or tentacles, and they might flow or bounce using simple local dynamic simulations,  even  if  they  did  not  influence  the  overall  dynamics.

5) Artificial  evolution permits  the  generation  of  complicated  virtual  systems  without requiring  design,  and  the  use  of  unbounded  genetic  languages allows  evolving  systems  to  increase  in  complexity  beyond  our understanding.