Evolving a virtual ecosystem with genetic algorithms

• Main Authors: Eccles, J.S., Dickerson, J.A., Junqing Shao
• Format: Conference Proceeding
• Language: English
• Subjects: Animation; Artificial neural networks; Computational modeling; Computer simulation; Ecosystems; Fuzzy systems; Genetic algorithms; Neural networks; Switches; Virtual environment
• DOI: 10.1109/CEC.2000.870374

A virtual ecosystem was developed using genetic algorithms, artificial neural networks, and fuzzy systems. The ecosystem simulated and regulated the motion and interactions of computer animated agents in a virtual environment. Within the ecosystem, each agent has its own neural networks that govern its motion strategy so that the creature could learn to perform different behaviors, such as searching for food and evading predators. The inputs of the neural networks were connected with creatures' eye-like sensors and the outputs of the networks were attached to creatures' legs to drive the creatures. The neural networks were evolved using genetic algorithms, including single tournament selection, two-point crossover, and one point mutation. Augmented fuzzy cognitive maps regulated the overall operation of the environment and allowed each creature to switch between different neural networks for finding food and avoiding predators. The experimental results demonstrated that animated agents can evolve and learn how to survive in a complex and dynamic virtual environment.