Evolving Virtual Creatures and Catapults

Evolving Virtual Creatures and Catapults

We present a system that can evolve the morphology and the controller of virtual walking and block-throwing creatures (catapults) using a genetic algorithm. The system is based on Sims' work, implemented as a flexible platform with an off-the-shelf dynamics engine. Experiments aimed at evolving Sims-type walkers resulted in the emergence of various realistic gaits while using fairly simple obje...

Evolving Adaptation in Virtual Creatures

The Problem: The simulated evolution of virtual creatures has produced many intriguing demonstrations, providing simple locomotion abilities and strategies for simple competetive games. However, to achieve a richer set of behaviours, adaptation within the individual’s lifetime is being explored. Can evolution be used to learn domain specific rules for solving the credit assignment problem and s...

Evolving Legged Locomotion in Virtual Creatures

Evolving Legged Locomotion of Virtual Creatures

Virtual reality (VR) systems require realistic simulation of arti cial worlds inhabited by virtual creatures. The complex behavior of these creatures has to be guided by intelligent control systems. The paper discusses experiments on combining an explicit planning method with evolutionary computation techniques for the creation of a control system for a six-legged virtual creature modeled in a ...

Evolving L-systems to generate virtual creatures