The field of metaheuristics for the application to combinatorial optimization problems is a rapidly growing field of research. This is due to the importance of combinatorial optimization problems for the scientific as well as the industrial world. We give a survey of the nowadays most important metaheuristics from a conceptual point of view. We outline the different components and concepts that are used in the different metaheuristics in order to analyze their similarities and differences. Two very important concepts in metaheuristics are intensification and diversification. These are the two forces that largely determine the behaviour of a metaheuristic. They are in some way contrary but also complementary to each other. We introduce a framework, that we call the I&D frame, in order to put different intensification and diversification components into relation with each other. Outlining the advantages and disadvantages of different metaheuristic approaches we conclude by pointing out the importance of hybridization of metaheuristics as well as the integration of metaheuristics and other methods for optimization.

We introduce a framework, called "physicomimetics," that provides distributed control of large collections of mobile physical agents in sensor networks. The agents sense and react to virtual forces, which are motivated by natural physics laws. Thus, physicomimetics is founded upon solid scientific principles. Furthermore, this framework provides an effective basis for self-organization, fault-tolerance, and self-repair. Three primary factors distinguish our framework from others that are related: an emphasis on minimality (e.g., cost effectiveness of large numbers of agents implies a need for expendable platforms with few sensors), ease of implementation, and run-time efficiency. Examples are shown of how this framework has been applied to construct various regular geometric lattice configurations (distributed sensing grids), as well as dynamic behavior for perimeter defense and surveillance. Analyses are provided that facilitate system understanding and predictability, including both qualitative and quantitative analyses of potential energy and a system phase transition. Physicomimetics has been implemented both in simulation and on a team of seven mobile robots. Specifics of the robotic embodiment are presented in the paper.

The paper reports on the application of genetic algorithms, probabilistic search algorithms based on the model of organic evolution, to NP-complete combinatorial optimization problems. In particular, the subset sum, maximum cut, and minimum tardy task problems are considered. Except for the fitness function, no problem-specific changes of the genetic algorithm are required in order to achieve results of high quality even for the problem instances of size 100 used in the paper. For constrained problems, such as the subset sum and the minimum tardy task, the constraints are taken into account by incorporating a graded penalty term into the fitness function. Even for large instances of these highly multimodal optimization problems, an iterated application of the genetic algorithm is observed to find the global optimum within a number of runs. As the genetic algorithm samples only a tiny fraction of the search space, these results are quite encouraging.

Evolutionary learning methods have been found to be useful in several areas in the development of intelligent robots. In the approach described here, evolutionary algorithms are used to explore alternative robot behaviors within a simulation model as a way of reducing the overall knowledge engineering effort. This paper presents some initial results of applying the SAMUEL genetic learning system to a collision avoidance and navigation task for mobile robots. 1 INTRODUCTION This is a progress report on our efforts to design intelligent robots for complex environments. The sort of applications we have in mind include sentry robots, autonomous delivery vehicles, undersea surveillance vehicles, and automated warehouse robots. In particular, we are investigating issues relating to machine learning, using multiple mobile robots to perform tasks such as playing hide-and-seek, tag, or competing to find hidden objects. Given the wide range of tasks in the area of robotics and learning, it may...

Autonomic computing systems reduce software maintenance costs and management complexity by taking on the responsibility for their configuration, optimization, healing, and protection. These tasks are accomplished by switching at runtime to a different system behaviour – the one that is more efficient, more secure, more stable, etc. – while still fulfilling the main purpose of the system. Thus, identifying and analyzing alternative ways of how the main objectives of the system can be achieved and designing a system that supports all of these alternative behaviours is a promising way to develop autonomic systems. This paper proposes the use of requirements goal models as a foundation for such software development process and sketches a possible architecture for autonomic systems that can be built using the this approach.

Several of the major transitions in evolutionary history, such as the symbiogenic origin of eukaryotes from prokaryotes, share the feature that existing entities became the components of composite entities at a higher level of organisation. This composition of pre-adapted extant entities into a new whole is a fundamentally different source of variation from the gradual accumulation of small random variations, and it has some interesting consequences for issues of evolvability. Intuitively, the pre-adaptation of sets of features in reproductively independent specialists suggests a form of 'divide and conquer' decomposition of the adaptive domain. Moreover, the compositions resulting from one level may become the components for compositions at the next level, thus scaling-up the variation mechanism. In this paper, we explore and develop these concepts using a simple abstract model of symbiotic composition to examine its impact on evolvability. To exemplify the adaptive capacity of the composition model, we employ a scale-invariant fitness landscape exhibiting significant ruggedness at all scales. Whilst innovation by mutation and by conventional evolutionary algorithms becomes increasingly more difficult as evolution continues in this landscape, innovation by composition is not impeded as it discovers and assembles component entities through successive hierarchical levels.

Abstract: Developments in computational models of evolutionary processes have led to the realisation of powerful, robust and general optimization and adaptive systems collectively called evolutionary algorithms. In this paper we provide an overview of evolutionary algorithms and consider the features and characteristics that are particularly appropriate for control engineering applications. The versatile and robust qualities of these algorithms are considered and a number of application areas described.

For many years, researchers in the field of mobile robotics have been investigating the use of genetic and evolutionary computation (GEC) to aid the development of mobile robot controllers. Alongside the fundamental choices of the GEC mechanism and its operators, which apply to both simulated and physical evolutionary robotics, other issues have emerged which are specific to the application of GEC to physical mobile robotics. This paper presents a survey of recent methods in GEC-developed mobile robot controllers, focusing on those methods that include a physical robot at some point in the learning loop. It simultaneously relates each of these methods to a framework of two orthogonal issues: the use of a simulated and/or a physical robot, and the use of finite, training phase evolution prior to a task and/or lifelong adaptation by evolution during a task. A list of evaluation criteria are presented and each of the surveyed methods are compared to them. Analyses of the framework and evaluation criteria suggest several possibilities; however, there appear to be particular advantages in combining simulated, training phase evolution (TPE) with lifelong adaptation by evolution (LAE) on a physical robot.

This paper presents an inductive learning system called the Genetic Instance-Based Learning (GIBL) system. This system combines instance-based learning approaches with evolutionary computation in order to achieve high accuracy in the presence of irrelevant or redundant attributes. Evolutionary computation is used to find a set of attribute weights that yields a high estimate of classification accuracy. Results of experiments on 16 data sets are shown, and are compared with a non-weighted version of the instance-based learning system. The results indicate that the generalization accuracy of GIBL is somewhat higher than that of the non-weighted system on regular data, and is significantly higher on data with irrelevant or redundant attributes.

Abstract not found