The advent of new families of reconfigurable integrated circuits makes it possible for artificial evolution to manipulate a real physical substrate to produce electronic circuits evaluated in the real world. This raises new issues about the potential nature of electronic circuits, because evolution uses no modelling, abstraction or analysis; only physical behaviour. The simplifying constraints of conventional design methodologies can be dropped, allowing evolution to exploit the full range of physical dynamics available from the silicon medium. This claim is investigated theoretically and in simulation, before presenting the first reported direct evolution of the configuration of a Field Programmable Gate Array (FPGA). Evolution is seen to harness its natural dynamics and exploit them in achieving a real-world task. 1 Introduction There is a type of Very-Large Scale Integrated circuit (a VLSI chip) known as a Field-Programmable Gate Array (FPGA). These chips do not have a predetermin...

Evolvable hardware (EHW) has attracted increasing attention since early 1990's with the advent of easily reconfigurable hardware such as field programmable gate arrays (FPGAs). It promises to provide an entirely new approach to complex electronic circuit design and new adaptive hardware. EHW has been demonstrated to be able to perform a wide range of tasks from pattern recognition to adaptive control. However, there are still many fundamental issues in EHW which remain open. This paper reviews the current status of EHW, discusses the promises and possible advantages of EHW, and indicates the challenges we must meet in order to develop practical and large-scale EHW. 1 Introduction Evolvable hardware (EHW) refers to hardware that can change its architecture and behaviour dynamically and autonomously by interacting with its environment. At present, almost all EHW uses an evolutionary algorithm (EA) as their main adaptive mechanism. One of the key motivations behind EHW is to learn from N...

True evolvable hardware should evolve whole hardware structures. In robotics, it is not enough only to evolve the control circuit --- the performance of the control circuit is dependent on other hardware parameters, the robot body plan, which might include body size, wheel radius, motor time constant, sensors, etc. Both control circuit and body plan co-evolve in true evolvable hardware. By including the robot body plan in the genotype as a kind of Hox gene, we co-evolve task-fulfilling behaviors and body plans, and we study the distribution of body parameters in the morphological space. Further, we have developed a new hardware module for the Khepera robot, namely ears with programmable amplifiers, synthesizers, and mixers, that allow us to study true evolvable hardware by modelling the evolution of auditory sensor morphology.

. The paper studies the role of neutrality in the fitness landscapes associated with the evolutionary design of digital circuits and particularly the three-bit binary multiplier. For the purpose of the study, digital circuits are evolved extrinsically on an array of logic cells. To evolve on an array of cells, a genotype-phenotype mapping has been devised by which neutrality can be embedded in the resulting fitness landscape. It is argued that landscape neutrality is beneficial for digital circuit evolution. 1 Introduction Digital circuit evolution is a process of evolving configurations of logic gates for some prespecified computational program. Often the aim is for a highly efficient electronic circuit to emerge in a population of instances of the program. Digital electronic circuits have been evolved intrinsically [1] and extrinsically [2--6]. The former is associated with an evolutionary process in which each evolved electronic circuit is built and tested on hardware, whil...

A major problem in the evolutionary design of combinational circuits is the problem of scale. This refers to the design of electronic circuits in which the number of gates required to implement the optimal circuit is too high to search the space of all designs in reasonable time, even by evolution. The reason is twofold: firstly, the size of the search space becomes enormous as the number of gates required to implement the circuit is increased, and secondly, the time required to calculate the fitness of a circuit grows as the size of the truth table of the circuit. This paper studies the evolutionary design of combinational circuits, particularly the three-bit multiplier circuit, in which the basic building blocks are small sub-circuits, modules inferred from other evolved designs. The structure of the resulting fitness landscapes is studied and it is shown that in general the principles of evolving digital circuits are scalable. Thus to evolve digital circuits using modules is faster...

Our experiences with a range of evolutionary robotic experiments have resulted in major changes to our set-up of artificial life experiments and our interpretation of observed phenomena. Initially, we investigated simulation-reality relationships in order to transfer our artificial life simulation work with evolution of neural network agents to real robots. This is a difficult task, but can, in a lot of cases, be solved with a carefully built simulator. By being able to evolve control mechanisms for physical robots, we were able to study biological hypotheses about animal behaviours by using exactly the same experimental set-ups as were used in the animal behavioural experiments. Evolutionary robotic experiments with rats open field box experiments and chick detours show how evolutionary robotics can be a powerful biological tool, and they also suggest that incremental learning might be fruitful for achieving complex robot behaviour in an evolutionary context. However, it is not enough...

of the work presented in this thesis has been previously published as listed below. Although some of these papers have co-authors, the work appearing in this thesis is entirely my own, with the exception of parts of chapter 3, which presents work jointly carried out by myself and Adrian Thompson. The respective contributions to this work will be explicitly stated at the beginning of the chapter. List of Previous Publications Kuntz, P., Layzell, P., & Snyers, D. (1997). A Colony of Ant-like Agents for Partitioning

. In this paper, the concept of hardware evolution is presented along with a newer approach to hardware evolution termed Complete Hardware Evolution (CHE). An experimental robot controller design --- GERC (Genetically Evolved Robot Controller), is described which uses CHE in the design process. The robot controller steers the robot around a given area trying to move as straight and as far as possible, exhibiting wall avoidance behaviour. By using CHE the whole evolution process is implemented on the same chip as the evolved circuit --- the robot steering circuitry. No external interaction is thus required to evaluate the robots behaviour during the evolution process. 1 Introduction Two main methods have been established for applying artificial evolution to the design of hardware systems. These are Extrinsic and Intrinsic evolution [dG93,ZPV96]. In Extrinsic (off-line) evolution, the evolution process and the resulting evaluations are implemented in software. Each individual, de...

Today’s reconfigurable technology provides vast parallelism that may be exploited in the design of a cellular computing machine. In this work a virtual Sblock FPGA is implemented on an existing FPGA, achieving not only an architecture in keeping with cellular computing principles but also suited to biologically inspired design methods. The design method proposed is a combination of evolution and development and results of running a developmental model on the cellular computing machine are presented.