Evolving 3D Morphology and Behavior by Competition

@article{Sims1994Evolving3M,
  title={Evolving 3D Morphology and Behavior by Competition},
  author={Karl Sims},
  journal={Artificial Life},
  year={1994},
  volume={1},
  pages={353-372}
}
  • K. Sims
  • Published 1994
  • Biology
  • Artificial Life
This article describes a system for the evolution and coevolution 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… 
The World of Framsticks: Simulation, Evolution, Interaction
TLDR
A three-dimensional virtual world simulation is described, where evolution takes place and it is possible to investigate behaviors of creatures in real-time and mimic spontaneous evolution when the fitness is defined as the life span of the organisms.
Sticky Feet - Evolution in a Multi-Creature Physical Simulation
TLDR
Artificial evolution is demonstrated in a system that combines physical simulation with competition between creatures that exhibit a wide array of body plans, locomotion styles, and interaction behaviors.
Co-Evolution and Ontogenetic Change in Competing Robots
TLDR
It is shown that predators benefit from forms of directional changes whereas prey attempt to exploit unpredictable behaviors in relation to open-ended evolution in unpredictably changing environments.
Evolving Virtual Creatures and Catapults
TLDR
The drop-kick strategy is found, as well as the systematic invention of the principle behind the wheel, when allowing mutations to the projectile in a system that can evolve the morphology and the controller of virtual walking and block-throwing creatures (catapults) using a genetic algorithm.
Co-Evolution and Ontogenetic Change inCompeting
We investigate the dynamics of competitive co-evolution in the framework of two miniature mobile robots, a predator with a vision system and a faster prey with proximity sensors. Both types of robots
Neuroevolution of Feedback Control for Object Manipulation by 3D Agents
TLDR
It is found that species evolving from scratch do no better or worse than those optimised for a different environment, and that sensory feedback is necessary for correct approach and control behaviours in agents, although close control is less dependent on sensory input than distance approach.
An Improved System for Artificial Creatures Evolution
TLDR
The present paper extends the feature set proposed by Sims, and describes the results of experiments based on the ‘box-grabbing’ coevolutionary task introduced by Sims.
Evolution of sustained foraging in three-dimensional environments with physics
TLDR
This work co-evolves the morphology and controller for virtual organisms in a three-dimensional physical environment to produce goal-directed locomotion in articulated agents and devised a strategy of evolutionary “staging”, where the best organism from a set of evolutionary experiments using a particular fitness function is used to seed a new set.
Dynamic Resolution in the Co-Evolution of Morphology and Control
TLDR
This paper presents a novel method for co-evolving morphology and control using CPPN-NEAT, capable of dynamically adjusting the resolution at which components of the robot are created.
Scalable co-optimization of morphology and control in embodied machines
TLDR
A technique for ‘morphological innovation protection’ is demonstrated, which temporarily reduces selection pressure on recently morphologically changed individuals, thus enabling evolution some time to ‘readapt’ to the new morphology with subsequent control policy mutations.
...
...

References

SHOWING 1-10 OF 24 REFERENCES
Evolving virtual creatures
  • K. Sims
  • Computer Science
    SIGGRAPH
  • 1994
TLDR
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 creatures that move and behave in simulated three-dimensional physical worlds.
Artificial evolution for computer graphics
  • K. Sims
  • Computer Science
    SIGGRAPH
  • 1991
TLDR
It is proposed that artificial evolution has potential as a powerful tool for achieving flexible complexity with a minimum of user input and knowledge of details.
Spacetime constraints revisited
TLDR
A global search algorithm that is capable of generating multiple novel trajectories for SC problems from scratch, and a genetic search algorithm for choosing behavior parameters that is currently implemented on a massively parallel computer.
Sensor-actuator networks
TLDR
A stochastic procedure for finding and then improving suitable SANs is given for physically-based animation of objects and ten different creatures controlled by this method are presented.
Competitive Environments Evolve Better Solutions for Complex Tasks
TLDR
It is demonstrated that competitive fitness functions, i.e. fitness functions that are dependent on the constituents of the population, can provide a more robust training environment than independent fitness functions.
Adaptation in natural and artificial systems
TLDR
Names of founding work in the area of Adaptation and modiication, which aims to mimic biological optimization, and some (Non-GA) branches of AI.
Genetic programming - on the programming of computers by means of natural selection
  • J. Koza
  • Computer Science
    Complex adaptive systems
  • 1993
TLDR
This book discusses the evolution of architecture, primitive functions, terminals, sufficiency, and closure, and the role of representation and the lens effect in genetic programming.
Competition, Coevolution and the Game of Tag
TLDR
In the experiments described here, control programs for mobile agents (simulated vehicles) are evolved based on their skill at the game of tag, guided by competitive fitness.
Plants, fractals, and formal languages
TLDR
An interesting class of procedural models of plants and trees is presented here which handles plant growth, sports an efficient data representation, and has a high “database amplification” factor.
...
...