In a previous SAB paper [10], we presented the scientific rationale for simulating the coevolution of pursuit and evasion strategies. Here, we present an overview of our simulation methods and some results. Our most notable results are as follows. First, co-evolution works to produce good pursuers and good evaders through a pure bootstrapping process, but both types are rather specially adapted to their opponents' current counter-strategies. Second, eyes and brains can also co-evolve within each simulated species -- for example, pursuers usually evolved eyes on the front of their bodies (like cheetahs), while evaders usually evolved eyes pointing sideways or even backwards (like gazelles). Third, both kinds of coevolution are promoted by allowing spatially distributed populations, gene duplication, and an explicitly spatial morphogenesis program for eyes and brains that allows bilateral symmetry. The paper concludes by discussing some possible applications of simulated pursuit-evasion ...

Most simulations of biological evolution depend on a rather restricted set of properties. In this paper a richer model, based on differential gene expression is introduced to control developmental processes in an artificial evolutionary system. Differential gene expression is used to get different cell types and to modulate cell division and cell death. One of the advantages using developmental processes in evolutionary systems is the reduction of the information needed in the genome to encode e.g. shapes or cell types which results in better scaling behavior of the system. My result showed that the shaping of multicellular organisms in 3d is possible with the proposed system.

This paper describes new genetic and developmental principles for an artificial evolutionary system (AES) and reports the first simulation results. Emphasis is placed on those developmental processes which reduce the length of the genome to code for a given problem. We exemplify the usefulness of developmental processes with cell growth, cell differentiation and the creation of neural control structures which we used to control a real world autonomous agent. The importance of including developmental processes relies much on the fact that a neural network can be specified implicitly by using cell-to-cell communication. 1 Introduction In the field of autonomous agents different approaches have been studied: One of them, the evolutionary approach, aims to produce increasingly sophisticated autonomous agents with no need to care about the details of the robots control structure. As others,(Nolfi et al.,1994; Cangelosi et al.,1994; Daellert & Beer,1994; Harvey et al.,1995), we are convinc...

Many arthropods (particularly insects) exhibit sophisticated visually guided behaviours. Yet in most cases the behaviours are guided by input from a few hundreds or thousands of "pixels " (i.e. ommatidia in the compound eye). Inspired by this observation, we have for several years been exploring the possibilities of visually guided robots with low-bandwidth vision. Rather than design the robot controllers by hand, we use artificial evolution (in the form of an extended genetic algorithm) to automatically generate the architectures for artificial neural networks which generate effective sensory-motor coordination when controlling mobile robots. Analytic techniques drawn from neuroethology and dynamical systems theory allow us to understand how the evolved robot controllers function, and to predict their behaviour in environments other than those used during the evolutionary process. Initial experiments were performed in simulation, but the techniques have now been successfully transferred to work with a variety of real physical robot platforms. This chapter reviews our past work, concentrating on the analysis of evolved controllers, and gives an overview of our current research. We conclude with a discussion of the application of our evolutionary techniques to problems in biological vision.

We present results from the concurrent evolution of visual sensing morphologies and sensory-motor controller-networks for visually guided robots. In this paper we analyse two (of many) networks which result from using incremental evolution with variable-length genotypes. The two networks come from separate populations, evolved using a common fitness function. The observable behaviours of the two robots are very similar, and close to the optimal behaviour. However, the underlying sensing morphologies and sensory-motor controllers are strikingly different. This is a case of convergent evolution at the behavioural level, coupled with divergent evolution at the morphological level. The action of the evolved networks is described. We discuss the process of analysing evolved artificial networks, a process which bears many similarities to analysing biological nervous systems in the field of neuroethology.

. In this paper we propose a biological inspired model to develop the structure of artificial neural networks. The model is based on an artificial genetic regualtory system, which controls the development of the neural network. The model allows for different cell types which are the result of different intercellular communication processes. Having different cells will lead to different development of connection patterns. The goal of the proposed model is to investigate the question how the local genetic processes are able to construct the structure of a neural network. 1 Introduction This paper reports on a computer model which is able to evolve artificial neural networks (ANN) in three dimensions. The proposed model is based on an artificial genetic regulatory system (AGRS) which controls the epigenetic processes of the development of an ANN by means of strictly local interactions between the cells and the genes. Since every cell contains the same genome, the differences between the ...

The generation of complex entities with advantageous behaviours beyond our manual design capability requires long-term incremental evolution with continuing emergence. In this paper, we argue that artificial selection models, such as traditional genetic algorithms, are fundamentally inadequate for this goal. Existing natural selection systems are evaluated, revealing both significant achievements and pitfalls. Thus, some requirements for the perpetuation of evolutionary emergence are established. An (artificial) environment containing simple virtual autonomous organisms with neural controllers has been created to satisfy these requirements and to aid in the development of an accompanying theory of evolutionary emergence. Resulting behaviours are reported alongside their neural correlates. In a particular example, the collective behaviour of one species provides a selective force which is overcome by another species, demonstrating the incremental evolutionary emergence of advantageous behaviours via naturally-arising coevolution. While the results fall short of the ultimate goal, experience with the system has provided some useful lessons for the perpetuation of emergence towards increasingly complex advantageous behaviours.

An artificial life entertainment-software product called Creatures was released in Europe in late 1996 and in the United States and Japan in mid-1997. When installed on a domestic computer (PC or Macintosh), each Creatures CD-ROM creates a virtual world in which autonomous software agents exist. The agents, known as "norns", interact with the human user, with each other, and with objects in their virtual world. Each norn coordinates perception and action via its own modular recurrent neural network: Each network has Hebbian learning, plus diffuse modulation of activity via a "hormonal" system that is part of that norn's "biochemistry". Details of each norn's neural network and biochemistry are genetically specified, and norns can breed via sexual reproduction. In the reproduction process, genetic material may be mutated and may also be subjected to "gene duplications" that enable potentially unlimited increases in complexity of the norns' design. Over 500,000 Creatures CD-ROMS have now been sold. As each installed copy of Creatures can support 5 to 10 simultaneously existing individual norns, it seems reasonable to estimate that there are up to 5 million norns existing in the "cyberspace" provided by the global Creatures user community.

The artificial evolution of intelligence is discussed with respect to current methods. An argument for withdrawal of the traditional `fitness function' in genetic algorithms is given on the grounds that this would better enable the emergence of intelligence, necessary because we cannot specify what intelligence is. A modular developmental system is constructed to aid the evolution of neural structures and a simple virtual world with many of the properties believed beneficial is set up to test these ideas. Resulting emergent properties are given, along with a brief discussion.

cognitive systems, biologicallyinspired computing, artificial life, artificial intelligence, autonomous agents This paper presents a review of the academic literature on biologically-inspired computing approaches to the science and engineering of cognitive systems. This review is intended as a rapid tour through the area (rather than a leisurely wander); and it should be readable in a few hours. The tour is partial in both senses of the word: it is only partially complete, and it is biased (i.e., it is not an