Division blocks and the open-ended evolution of development, form, and behavior

We present a new framework for artificial life involving physically simulated, three-dimensional blocks called Division Blocks. Division Blocks can grow and shrink, divide and form joints, exert forces on joints, and exchange resources. They are controlled by recurrent neural networks that evolve, along with the blocks, by natural selection. Division Blocks are simulated in an environment in which energy is approximately conserved, and in which all energy derives ultimately from a simulated sun via photosynthesis. In this paper we describe our implementation of Division Blocks and some of the ways that it can support experiments on the openended evolution of development, form, and behavior. We also present preliminary data from simulations, demonstrating the reliable emergence of cooperative resource transactions. Categories and Subject Descriptors I.2.11 [Artificial Intelligence]: Distributed Artificial Intelligence—Multiagent systems; I.2.6 [Artificial Intelligence]: Learning�...

• Type: Conference
• Year: 2007
• Where: GECCO
• Authors: Lee Spector, Jon Klein, Mark Feinstein
• Keywords: Artificial Life, Blocks Called Division, Division Blocks, GECCO 2007