The goal of getting computers to automatically solve problems is central to artificial intelligence, machine learning, and the broad area encompassed by what Turing called “machine intelligence ” [161, 162].

Most multi-agent systems are inspired by classical AI, whose objective was to realize humanlevel intelligence in a computer. As the field has moved toward multiple agents, there has been a presumption that individual agents still aspire to high-level intelligence. Swarming systems follow an alternative model, inspired more by artificial life than artificial intelligence. The individual agents in these systems may be non-cognitive, but complex, robust cognition emerges from their interactions. This paper defines swarming and the concepts of self-organization and emergence that underlie it. It describes the kinds of problems for which it is well suited, explores why it functions, and outlines some initial principles of an engineering methodology for developing artificial swarming systems.

Discussions of agent interactions frequently characterize behavior as Coherent, collaborative, cooperative, competitive, or coordinated. We propose a series of formal distinctions among these terms and several others. We argue that all of these are specializations of the more foundational category of correlation, which can be measured by the joint information of a system. We also propose congruence as a category orthogonal to the others, reflecting the degree to which correlation and its specializations satisfy user requirements. Then we explore the degree to which lack of correlation can arise purposefully, and show the need to use formal stochasticity in cases where such lack of correlation is truly necessary (such as in stochastic search). Keywords Coordination, correlation, competition, contention, cooperation, congruence, communication, command, constraint, construction, conversation, stigmergy, agent interaction 1.

Abstract. Internet based parallel genetic programming (GP) creates fractal patterns like Koch’s snow flake. Pfeiffer,

Abstract. In recent years, mobile ad-hoc networks (MANETs) have been deployed in various scenarios, but their scalability is severely restricted by the human operators ’ ability to configure and manage the network in the face of rapid change of the network structure and demand patterns. In this paper, we present a self-organizing approach to MANET management that follows general principles of engineering swarming applications. 1

We review the applications of artificial life (ALife), the creation of synthetic life on computers to study, simulate, and understand living systems. The definition and features of ALife are shown by application studies. ALife application fields treated include robot control, robot manufacturing, practical robots, computer graphics, natural phenomenon modeling, entertainment, games, music, economics, Internet, information processing, industrial design, simulation software, electronics, security, data mining, and telecommunications. In order to show the status of ALife application research, this review primarily features a survey of about 180 ALife application articles rather than a selected representation of a few articles. Evolutionary computation is the most popular method for designing such applications, but recently swarm intelligence, artificial immune network, and agent-based modeling have also produced results. Applications were initially restricted to the robotics

I would like to thank Dr. Richard Povinelli for his consistent support and encouragement in the past three years. His initial ideas, insightful suggestions, and wise management have made the completion of this work possible. I have learned a lot from working with him, his active attitude towards research, his earnest, his preciseness, and his humor. I am grateful to my committee members, Drs. Xin Feng, Michael Johnson, and Jeffrey Hock, who have provided great comments and suggestions to this thesis. I thank my labmates, Felice Roberts, Bin Chen, Xiaolin Liu, and all our Computational Intelligence Seminar members. They have given me a lot of help during my research. I am grateful to Marquette University for its financial support of this research, and the faculty of the Electrical and Computer Engineering Department for providing a great environment for studying and researching. I am deeply grateful to my parents, for their constant support, care, and love. ii

rather than starting out with such behavior. Naturally, he concluded that we should enact a procession of learning stages during which a machine could "grow" in knowledge. He termed this a child machine, which would learn more or less quickly (depending on its construction) by following its own developmental process. Turing anticipated that a systematic process would produce the child machine, but he did not rule out a random element in its construction and indeed pointed to the natural evolutionary process 74 IEEE INTELLIGENT SYSTEMS Genetic programming A wide range of core concepts in AI---and in computer science in general---can be traced to computational metaphors inspired by a rich variety of phenomena in the natural world. One of the best examples is neural networks, whose core ideas are based on the functioning of systems of neurons in the brain. This issue's Trends and Controversies concerns genetic programming (GP), whose inspiration com

INTRODUCTION The goal of getting computers to automatically solve problems is central to artificial intelligence, machine learning, and the broad area encompassed by what Turing called "machine intelligence" (Turing, 1948, 1950). In his talk entitled AI: Where It Has Been and Where It Is Going, machine learning pioneer Arthur Samuel stated the main goal of the fields of machine learning and artificial intelligence: [T]he aim [is] ... to get machines to exhibit behavior, which if done by humans, would be assumed to involve the use of intelligence. (Samuel, 1983) Genetic programming is a systematic method for getting computers to automatically solve a problem starting from a high-level statement of what needs to be done. Genetic programming is a domain-independent method that genetically breeds a population of computer programs to solve a problem. Specifically, genetic programming iteratively transforms a population of computer programs into a new generation of programs by applying

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.