This paper presents an autonomous agent-based image segmentation approach. In this approach, a digital image is viewed as a two-dimensional cellular environment in which the agents inhabit and attempt to label homogeneous segments. In so doing, the agents rely on some reactive behaviors such as breeding and diffusion. The agents that are successful in finding the pixels of a specific homogeneous segment will breed offspring agents inside their neighboring regions. Hence, the offspring agents will become likely to find more homogeneous-segment pixels. In the mean time, the unsuccessful agents will be inactivated, without further search in the environment. Index terms: Distributed autonomous agents, reactive behavior, evolutionary computation, breeding, diffusion, homogeneous-segment searching, adaptive image segmentation, and agent dynamics. I. INTRODUCTION The work to be presented in this paper explores an autonomous agent-based approach to image segmentation. In image segmentation, o...

This paper presents a new approach to solving N-queen problems, which involves a model of distributed autonomous agents with artificial life (ALife) and a method of representing N-queen constraints in an agent environment. The distributed agents locally interact with their living environment, i.e., a chessboard, and execute their reactive behaviors by applying their behavioral rules for randomized motion, least-conflict position searching, and cooperating with other agents etc. The agent-based N-queen problem solving system evolves through selection and contest according to the rule of Survival of the Fittest, in which some agents will die or be eaten if their moving strategies are less efficient than others. The experimental results have shown that this system is capable of solving large-scale N-queen problems. This paper also provides a model of ALife agents for solving general CSPs

Object-oriented programming has worked quite well – so far. What are the objects, how do they relate to each other? Once we clarified these questions we typically feel confident to design and implement even the most complex systems. However, objects can deceive us. They can lure us into a false sense of understanding. The metaphor of objects can go too far by making us try to create objects that are too much inspired by the real world. This is a serious problem, as a resulting system may be significantly more complex than it would have to be, or worse, will not work at all. We postulate the notion of an antiobject as a kind of object that appears to essentially do the opposite of what we generally think the object should be doing. As a Gedankenexperiment antiobjects allow us to literally think outside the proverbial box or, in this case outside the object. This article discusses two examples, a Pacman game and a soccer simulation where antiobjects are employed as part of a game AI called Collaborative Diffusion. In Collaborative-Diffusion based soccer the player and grass tile agents are antiobjects. Counter to the intuition of most programmers the grass tile agents, on top of which all the players are moving, are doing the vast majority of the computation, while the soccer player agents are doing almost no computation. This article illustrates that this role reversal is not only a different way to look at objects but, for instance, in the case with Collaborative Diffusion, is simple to implement, incremental in nature and more robust than traditional approaches.

Autonomous multi-entity systems are plentiful in natural and artificial worlds. Many systems have been studied in depth and some models of them have been built as computational systems for problem solving. Central to these computational systems is the notion of autonomy. This article surveys research work done along this direction and proposes autonomy oriented computing (AOC) as a paradigm to describe systems for solving hard computational problems and for characterizing the behaviors of a complex system. AOC differs from major complex system related studies such as artificial life, simulated evolution, and multi-agent systems in that AOC is not just intended to replicate complex behavior, emulate evolution, or coordinate the functioning of many interacting agents. AOC emphasizes the modeling of autonomy in the entities of a complex system and the self-organization of them in achieving a specific goal. Through examining implemented applications, we identify three main approaches to AOC. Specifically, we provide a detailed description of the AOC framework with formal definitions of essential constructs and their interrelationships, including the notions of emergent autonomy, self-organization, and the interactions among entities and environment.

this paper, we extend and modify the ERA approach proposed in Ref. 13 to solve Propositional Satisfiability Problems (SATs). The new ERA approach involves a multiagent system where each agent only senses its local environment and applies some self-organizing rules for governing its movements. The environment, which is a two-dimensional cellular environment, records and updates the local values that are computed and a#ected according to the movements of individual agents. In solving a SAT with the ERA approach, we first divide variables into several groups, and represent each variable group with an agent whose possible positions correspond to the elements in a Cartesian product of variable domains, and then randomly place each agent onto one of its possible positions. Thereafter, the ERA system will keep on dispatching agents to choose their movements until an exact or approximate solution emerges

Examples of autonomous multi-entity systems are plentiful, both in the natural and artificial worlds. Many systems have been studied in depth and some models of these have been built in computational systems for problem solving. Central to these computational systems is the notion of autonomy. This article proposes autonomy oriented computation (AOC) as a complementary paradigm for solving hard computational problems and for characterizing the behaviors of a complex system.

Facing the increasing needs for large-scale, robust, adaptive, and distributed/decentralized computing capabilities [1, 5] from such fields as Web intelligence, scientific and social computing, Internet commerce, and pervasive computing, an unconventional bottom-up paradigm, based on the notions of Autonomy-Oriented Computing (AOC) and self-organization in open complex systems, offers new opportunities for developing promising architectures, methods, and technologies. The goal of this paper is to describe the key concepts in this computing paradigm, and furthermore, discuss some of the fundamental principles and mechanisms for obtaining self-organized computing solutions. 1.

In this article, we take a look at an emerging computing paradigm called Nature Inspired Computing (NIC). We examine the impacts of NIC in two aspects. First, NIC enables us to explain the underlying mechanism of a real-world complex system by formulating computing models and testing hypotheses through controlled experimentation. The end product of such computing experiments is a deep understanding or a new discovery of the real working mechanism of the modeled system. Second, NIC enables us to embody autonomous (e.g., life-like) behavior in solving computing problems. With detailed knowledge of the underlying mechanism, abstracted autonomous behavior can be used as a model for a general-purpose problem-solving strategy or method. Formulation and Characteristics of NIC Generally speaking, the objectives of NIC are twofold: (1) characterizing and understanding complex phenomena or systems behavior, and (2) designing and developing computing solutions to hard problems. Neither of these objectives can be achieved without formulating a model of the factors underlying a complex system. The modeling process can be started with a theoretical analysis from a macroscopic or microscopic view of the system. Alternatively, a blackbox or whitebox approach may be adopted. Blackbox approaches such as Markov models or artificial neural networks normally do not tell us much about the working mechanism. On the other hand, whitebox approaches such as agents with bounded rationality are more useful for explaining behavior [10]. NIC Formulation. The essence of NIC formulation lies in the conception of a computing system that is operated by population(s) of autonomous entities. The rest of the system is referred to as the environment. An autonomous entity consists of a detector (or a set of detectors), an effector (or again, a set of effectors), and a repository of local behavior rules (see Figure 1) [5][8].

In this paper, we present a self-organized computing approach to solving hard combinatorial optimization problems, e.g., the traveling salesman problem (TSP). First of all, we provide an analytical characterization of such an approach, by means of formulating combinatorial optimization problems into autonomous multi-entity systems and thereafter examining the microscopic characteristics of optimal solutions with respect to discrete state variables and local fitness functions. Next, we analyze the complexity of searching in the solution space based on the representation of fitness network and the observation of phase transition. In the second part of the paper, following the analytical characterization, we describe a decentralized, self-organized algorithm for solving combinatorial optimization problems. The validation results obtained by testing on a set of benchmark TSP instances have demonstrated the effectiveness and efficiency of the proposed algorithm. The link established between the microscopic characterization of hard computational systems and the design of self-organized computing methods provides a new way of studying and tackling hard combinatorial optimization problems.

formation system. After detailing the results obtained from the developed system, some discussion is offered on the future of such systems, what difficulties were encountered in the work and some directions for further research in the area. iii Acknowledgements. Thanks to Seth Bullock for all his support since Summer 2001. Recognition is also due to everyone at the Bio-systems Reading Group this year -- Seth Bullock, Jason Noble, John Cartlidge, Dave Harris, Dan Franks, Richard Marston and Neil Meikle -- for the stimulating discussion, whether on topic or not. Last (but by no means least), thanks to you Sarah Stewart -- these past few months your love and support have proved indispensable. iv Contents Summary ............................................................................................................................. ii Minimum Requirements.........................................................................