Abstract | In this paper we describe the evolution of a discrete-time recurrent neural network to control a real mobile robot. In all our experiments the evolutionary procedure is carried out entirely on the physical robot without human intervention. We showthat the autonomous development of a set of behaviors for locating a battery charger and periodically returning to it can be achieved by lifting constraints in the design of the robot/environment interactions that were employed in a preliminary experiment. The emergent homing behavior is based on the autonomous development ofaninternal neural topographic map (which is not pre-designed) that allows the robot to choose the appropriate trajectory as function of location and remaining energy.

Evolutionary computation has started to receive significant attention during the last decade, although the origins can be traced back to the late 1950s. This article surveys the history as well as the current state of this rapidly growing field. We describe the purpose, the general structure and the working principles of different approaches, including genetic algorithms (GA) (with links to genetic programming (GP) and classifier systems (CS)), evolution strategies (ES), and evolutionary programming (EP), by analysis and comparison of their most important constituents (i.e., representations, variation operators, reproduction and selection mechanism). Finally, we give a brief overview on the manifold of application domains, although this necessarily must remain incomplete.

It is argued that competitive co-evolution is a viable methodology for developing truly autonomous and intelligent machines capable of setting their own goals in order to face new and continuously changing challenges. The paper starts giving an introduction to the dynamics of competitive co-evolutionary systems and reviews their relevance from a computational perspective. The method is then applied to two mobile robots, a predator and a prey, which quickly and autonomously develop efficient chase and evasion strategies. The results are then explained and put in a longterm framework resorting to a visualization of the Red Queen effect on the fitness landscape. Finally, comparative data on different selection criteria are used to indicate that co-evolution does not optimize "intuitive" objective criteria. 1. Competitive Co-Evolution In a competitive co-evolutionary system the survival probability of a species is affected by the behavior of the other species. In the simplest scenario of...

Given a parallel program represented by a task graph, the objective of a scheduling algorithm is to minimize the overall execution time of the program by properly assigning the nodes of the graph to the processors. This multiprocessor scheduling problem is NP-complete even with simplifying assumptions, and becomes more complex under relaxed assumptions such as arbitrary precedence constraints, and arbitrary task execution and communication times. The present literature on this topic is a large repertoire of heuristics that produce good solutions in a reasonable amount of time. These heuristics, however, have restricted applicability in a practical environment because they have a number of fundamental problems including high time complexity, lack of scalability, and no performance guarantee with respect to optimal solutions. Recently, genetic algorithms (GAs) have been widely reckoned as a useful vehicle for obtaining high quality or even optimal solutions for a broad range of combinato...

. A massively parallel genetic algorithm for the mapping and scheduling problem is presented. It turns out that a standard genetic algorithm package can easily be adapted to the mapping and scheduling problem. The resulting algorithm is able to exploit parallelism of a massively parallel hardware and can solve larger problems than a reference algorithm. Moreover the algorithm is well suited if the algorithm has to be restarted with a slightly modified problem input. The algorithm is implemented on the array processor MasPar MP-1. 1 Introduction This paper presents a heuristic for the mapping and scheduling problem using genetic algorithms. This optimization problem is known to be NP-hard, so a heuristic seems to be appropriate. Moreover the problem arises in the context of parallelizing compilers, so a parallelizable heuristic should be considered. Both qualities are matched by genetic algorithms. A second goal of this paper is to show that genetic algorithms can be used as a standard...

Evolutionary computation can be conducted at various levels of abstraction (e.g., genes, individuals, species). Recent claims have been made that simulated evolution can be made more biologically accurate by applying specific genetic operators that mimic low-level transformations to DNA. This paper argues instead that the appropriateness of particular variation operators depends on the level of abstraction of the simulation. Further, including specific random variation operators simply because they have a similar form as genetic operators that occur in nature does not, in general, lead to greater fidelity in simulation. 1. Introduction Evolution is characterized by distinct levels of hierarchy (e.g., species, individuals, chromosomes, genes), and quite naturally so is evolutionary computation. Typically, the elements in a simulated evolving population are considered to be analogous to species in evolutionary programming [9], individuals in evolution strategies [20], and chromos...

Recurrent neural networks have become popular models for system identification and time series prediction. Nonlinear autoregressive models with exogenous inputs (NARX) neural network models are a popular subclass of recurrent networks and have been used in many applications. Although embedded memory can be found in all recurrent network models, it is particularly prominent in NARX models. We show that using intelligent memory order selection through pruning and good initial heuristics significantly improves the generalization and predictive performance of these nonlinear systems on problems as diverse as grammatical inference and time series prediction.

In this paper I explore the hypothesis that some of today robots might possess a form of consciousness whose substrate is a mere algorithm. First, consciousness is defined within an evolutionary framework as awareness of one's own state in relation to the external environment. Then, the basic prerequisites for such conscious activity are discussed, namely embodiment, autonomy, and adaptation mechanisms. Artificial evolution, rather than evolutionary optimisation, is presented as a viable methodology to create conscious robots, accompanied by some examples of behaviours of artificially evolved robots. Finally, I argue that what might be problematic with the concept of robot consciousness is not the robot, but the notion of consciousness itself. 1 Paving the Road to Robot Consciousness Could the ordered list of operations which forms any computer algorithm constitute the basis of consciousness for a robot? "Of course not", would be the sensible answer probably given by most readers with...

This paper reviews recent advances in supervised learning with a focus on two most important issues: performance and efficiency. Performance addresses the generalization capability of a learning machine on randomly chosen samples that are not included in a training set. Efficiency deals with the complexity of a learning machine in both space and time. As these two issues are general to various learning machines and learning approaches, we focus on a special type of adaptive learning systems with a neural architecture. We discuss four types of learning approaches: training an individual model; combinations of several well-trained models; combinations of many weak models; and evolutionary computation of models. We explore advantages and weaknesses of each approach and their interrelations, and we pose open questions for possible future research.

.............................................................................................................................................. xix Chapter 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .1 1.1 Overview.................................................................................................................................. 1 1.2 Parallel Architectures and The Scheduling Problem......................................................... 3 1.3 Research Objectives ................................................................................................................ 5 1.4 Contributions........................................................................................................................... 6 1.5 Organization of the Thesis .................................................................................................... 7 Chapter 2 Background and Literature Survey . . . . . . . . . . . . . . ...