Evolved Virtual Creatures

Inhaltliche Beschreibung

"Evolved Virtual Creatures" is a computer animated demonstration of research results that show simulated block creatures performing various evolved behaviors.
The research focus was to describe a system for the evolution and co-evolution of virtual creatures that compete in physically simulated three-dimensional worlds. Pairs of individuals enter one-on-one contests in which they contend to gain control of a common resource. The winners receive higher relative fitness scores allowing them to survive and reproduce. Realistic dynamics simulation including gravity, collisions, and friction, restricts the actions to physically plausible behaviors.
The morphology of these creatures and the neural systems for controlling their muscle forces are both genetically determined, and the morphology and behavior can adapt to each other as they evolve simultaneously. The genotypes are structured as directed graphs of nodes and connections, and they can efficiently but flexibly describe instructions for the development of creatures’ bodies and control systems with repeating or recursive components. When simulated evolutions are performed with populations of competing creatures, interesting and diverse strategies and counter-strategies emerge. (Karl Sims)

• › Siggraph Proceedings [PDF | 79 KB ] [link 02]
• › Artificial Life IV Proceedings [PDF | 87 KB ] [link 03]

Technische Beschreibung

The morphologies of creatures and the neural systems for controlling their muscle forces are both generated automatically using genetic algorithms. Different fitness evaluation functions are used to direct simulated evolutions towards specific behaviors such as swimming, walking, jumping, and following. A genetic language is presented that uses nodes and connections as its primitive elements to represent directed graphs, which are used to describe both the morphology and the neural circuitry of these creatures. This genetic language defines a hyperspace containing an indefinite number of possible creatures with behaviors, and when it is searched using optimization techniques, a variety of successful and interesting locomotion strategies emerge, some of which would be difficult to invent or build by design.

The genetic algorithm is a form of artificial evolution, and is a commonly used method for optimization. A Darwinian "survival of the fittest" approach is employed to search for optima in large multidimensional spaces. Genetic algorithms permit virtual entities to be created without requiring an understanding of the procedures or parameters used to generate them. The measure of success, or fitness, of each individual can be calculated automatically, or it can instead be provided interactively by a user. Interactive evolution allows procedurally generated results to be explored by simply choosing those that are the most aesthetically desirable for each generation.
The user sacrifices some control when using these methods, especially when the fitness is procedurally defined. However, the potential gain in automating the creation of complexity can often compensate for this loss of control, and a higher level of user influence is still maintained by the fitness criteria specification.

Hardware / Software

Software and Animation: Karl Sims
Hardware: Connection Machine CM-5

Statement

The "Evolved Virtual Creatures" project was developed in 1994 at Thinking Machines Corporation. I was an Artist in Residence there,
and was given the task of showing the computational ability of their Connection Machine (one of the first parallel processing supercomputers) in a visually demonstrable way.
This was the last project of a series, the others being 3d animations ("Panspermia", "Primordial Dance", and "Liquid Selves") and the interactive exhibit "Genetic Images".

Veröffentlichungen

• Sims, K.arl: "Evolving Virtual Creatures"; in: Computer Graphics (Siggraph '94 Proceedings, Annual Conference Series), Juli 1994, S.15-22.
• Sims, Karl: "Evolving 3D Morphology and Behavior by Competition"; in: Artificial Life IV Proceedings, MIT Press, 1994, S.28-39.
• Sims, Karl: "Artificial Evolution for Computer Graphics"; in: Computer Graphics, Vol.25, Nr.4, Juli 1991, S.319-328.
• Sims, Karl: "Interactive Evolution of Dynamical Systems." In: Varela, Francisco (Hrsg.): Proceedings of the First European Conference on Artificial Life: Toward a Practice of Autonomous Systems, MIT Press, 1992, S.171-178.