Evolving Virtual Creatures and Catapults

Evolution of Virtual Catapults

We describe the re-implementation of a system to evolve the morphology and behavior of artificial creatures, originally due to Karl Sims. The new implementation is fast, flexible, and allows for the evolution of a range of novel behaviors not previously seen in Sims’ or related work. In particular, we use off-the-shelf dynamics simulator engines that can be exchanged on the fly, and introduce a...

Evolving a Diversity of Creatures through Novelty Search and Local Competition

An ambitious challenge in artificial life is to craft an evolutionary process that discovers a wide diversity of welladapted virtual creatures within a single run. Unlike in nature, evolving creatures in virtual worlds tend to converge to a single morphology because selection therein greedily rewards the morphology that is easiest to exploit. However, novelty search, a technique that explicitly...

Evolving Legged Locomotion in Virtual Creatures

Evolving Amphibian Behavior in Complex Environment

In this study, we aim to evolving autonomous virtual creatures which have complex shapes in a complex environment. We implement a basic physics law and fluid influences with a virtual environment and evolve artificial creatures in plural environments (on the ground, in the water). Each model, which is evolved in a different environment, obtains an effective moving behavior in each environment (...

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 ...