Showing papers on "Swarm behaviour published in 2003"

Stability analysis of swarms

Abstract: In this note, we specify an "individual-based" continuous-time model for swarm aggregation in n-dimensional space and study its stability properties. We show that the individuals (autonomous agents or biological creatures) will form a cohesive swarm in a finite time. Moreover, we obtain an explicit bound on the swarm size, which depends only on the parameters of the swarm model.

Data clustering using particle swarm optimization

Abstract: This paper proposes two new approaches to using PSO to cluster data. It is shown how PSO can be used to find the centroids of a user specified number of clusters. The algorithm is then extended to use K-means clustering to seed the initial swarm. This second algorithm basically uses PSO to refine the clusters formed by K-means. The new PSO algorithms are evaluated on six data sets, and compared to the performance of K-means clustering. Results show that both PSO clustering techniques have much potential.

Bare bones particle swarms

Abstract: The particle swarm algorithm has just enough moving parts to make it hard to understand. The formula is very simple, it is even easy to describe the working of the algorithm verbally, yet it is very difficult to grasp in one's mind how the particles oscillate around centers that are constantly changing; how they influence one another; how the various parameters affect the trajectory of the particle; how the topology of the swarm affects its performance; and so on. This paper strips away some traditional features of the particle swarm in the search for the properties that make it work. The particle swarm algorithm is modified by eliminating the velocity formula. Variations are compared. In the process some of the mysteries of the algorithm are revealed, we discover its similarity to other stochastic population-based problem solving methods, and new avenues of investigation are suggested or implied.

Particle swarm optimization

Abstract: Gerhard Venter (gventer_vrand.conl) *Vanderpla(ds Research and Development, bit.1767 S 8th St'reef. Suite 100, Colorado Springs. CO 80906Jaroslaw Sobieszczanski-Sobieski (j.sobieski:_larc.nasa.gov) *A_4SA Lcmgley Research Ce,_terMS 240, Hampton, I:4 23681-2199The purpose of this paper is to show how the search algorithm, known as par-ticle swarm optimization performs. Here, particle swarm optimization ks appliedto structural design problems, but the method.has a much wider range of possi-ble applications. The paper's new contributions are improvements to the particleswarm optimization algorithm and conclusions and recommendations as to theutility of the algorithm. Results of numerical experiments for both continuousand discrete applications are presented in the paper. The results indicate that theparticle swarm optimization algorithm does locate the constrained minimum de-sign in continuous applications with very good precision, albeit at a much highercomputational cost than that of a typical gradient based optimizer. However, thetrue potential of particle swarm optimization is primarily in applications withdiscrete and/or discontinuous functions and variables. Additionally, particleswarm optimization has the potential of e3_icient computation with very largenumbers of concurrently operating processors.

Mutual interactions, potentials, and individual distance in a social aggregation

Abstract: We formulate a Lagrangian (individual-based) model to investigate the spacing of individuals in a social aggregate (e.g., swarm, flock, school, or herd). Mutual interactions of swarm members have been expressed as the gradient of a potential function in previous theoretical studies. In this specific case, one can construct a Lyapunov function, whose minima correspond to stable stationary states of the system. The range of repulsion (r) and attraction (a) must satisfy r cAa(d+1) where R, A are magnitudes, c is a constant of order 1, and d is the space dimension) to avoid collapse of the group to a tight cluster. We also verify the existence of a well-spaced locally stable state, having a characteristic individual distance. When the number of individuals in a group increases, a dichotomy occurs between swarms in which individual distance is preserved versus those in which the physical size of the group is maintained at the expense of greater crowding.

Stability analysis of M-dimensional asynchronous swarms with a fixed communication topology

Abstract: Coordinated dynamical swarm behavior occurs when certain types of animals forage for food or try to avoid predators. Analogous behaviors can occur in engineering systems (e.g., in groups of autonomous mobile robots or air vehicles). In this paper, we study a model of an M-dimensional (M/spl ges/2) asynchronous swarm with a fixed communication topology, where each member only communicate with fixed neighbors, to provide conditions under which collision-free convergence can be achieved with finite-size swarm members that have proximity sensors, and neighbor position sensors that only provide delayed position information. Moreover, we give conditions under which an M-dimensional asynchronous mobile swarm with a fixed communication topology following an "edge-leader" can maintain cohesion during movements even in the presence of sensing delays and asynchronism. In addition, the swarm movement flexibility is analyzed. Such stability analysis is of fundamental importance if one wants to understand the coordination mechanisms for groups of autonomous vehicles or robots, where intermember communication channels are less than perfect and collisions must be avoided.

Particle swarm optimization with mutation

Abstract: The particle swarm optimization algorithms converges rapidly during the initial stages of a search, but often slows considerably and can get trapped in local optima. This paper examines the use of mutation to both speed up convergence and escape local minima. It compares the effectiveness of the basic particle swarm optimization scheme (BPSO) with each of BPSO with mutation, constriction particle swarm optimization (CPSO) with mutation, and CPSO without mutation. The four test functions used were the Sphere, Ackley, Rastrigin and Rosenbrock functions of dimensions 10, 20 and 30. The results show that mutation hinders the motion of the swarm on the sphere but the combination of CPSO with mutation provides a significant improvement in performance for the Rastrigin and Rosenbrock functions for all dimensions and the Ackley function for dimensions 20 and 30, with no improvement for the 10 dimensional case.

Sizing design of truss structures using particle swarms

Abstract: The optimal sizing design of truss structures is studied using the recently proposed particle swarm optimization algorithm (PSOA). The algorithm mimics the social behavior of birds. Individual birds in the flock exchange information about their position, velocity and fitness, and the behavior of the flock is then influenced to increase the probability of migration to regions of high fitness. A simple approach is presented to accommodate the stress and displacement constraints in the initial stages of the swarm searches. Increased social pressure, at the cost of cognitive learning, is exerted on infeasible birds to increase their rate of migration to feasible regions. Numerical results are presented for a number of well-known test functions, with dimensionality of up to 21.

Watch thy neighbor or how the swarm can learn from its environment

Abstract: Particle swarm optimization is a novel algorithm where a population of candidate problem solution vectors evolves "social" norms by being influenced by their topological neighbors. Until now, an individual was influenced by its best performance acquired in the past and the best experience observed in its neighborhood. In this paper, we introduce new ways an individual can be influenced by its neighbors.

Evolving aggregation behaviors in a swarm of robots

Abstract: In this paper, we study aggregation in a swarm of simple robots, called s-bots, having the capability to self-organize and self- assemble to form a robotic system, called a swarm-bot The aggregation process, observed in many biological systems, is of fundamental impor- tance since it is the prerequisite for other forms of cooperation that in- volve self-organization and self-assembling We consider the problem of defining the control system for the swarm-bot using artificial evolution The results obtained in a simulated 3D environment are presented and analyzed They show that artificial evolution, exploiting the complex in- teractions among s-bots and between s-bots and the environment, is able to produce simple but general solutions to the aggregation problem

Stability analysis of one-dimensional asynchronous swarms

Abstract: Coordinated swarm behavior in certain types of animals can also occur in groups of autonomous vehicles. Swarm "cohesiveness" is characterized as a stability property. Conditions for one-dimensional asynchronous swarms to achieve collision-free convergence even in the presence of sensing delays and asynchronism during movements are provided. Each finite-size swarm member has proximity sensors and neighbor position sensors that only provide delayed position information. Such stability analysis is of fundamental importance if one wants to understand the coordination mechanisms for "platoons" of autonomous vehicles, where intermember communication channels are less than perfect and collisions must be avoided.

Transport modeling by multi-agent systems: a swarm intelligence approach

Abstract: There are a number of emergent traffic and transportation phenomena that cannot be analyzed successfully and explained using analytical models. The only way to analyze such phenomena is through the development of models that can simulate behavior of every agent. Agent-based modeling is an approach based on the idea that a system is composed of decentralized individual ‘agents’ and that each agent interacts with other agents according to localized knowledge. The agent-based approach is a ‘bottom-up’ approach to modeling where special kinds of artificial agents are created by analogy with social insects. Social insects (including bees, wasps, ants and termites) have lived on Earth for millions of years. Their behavior in nature is primarily characterized by autonomy, distributed functioning and self-organizing capacities. Social insect colonies teach us that very simple individual organisms can form systems capable of performing highly complex tasks by dynamically interacting with each other. On the other h...

Swarm robotic odor localization: Off-line optimization and validation with real robots

Abstract: This paper presents an investigation of odor localization by groups of autonomous mobile robots using principles of Swarm Intelligence. First, we describe a distributed algorithm by which groups of agents can solve the full odor localization task more efficiently than a single agent. Next, we demonstrate that a group of real robots under fully distributed control can successfully traverse a real odor plume, and that an embodied simulator can faithfully reproduce these real robots experiments. Finally, we use the embodied simulator combined with a reinforcement learning algorithm to optimize performance across group size, showing that it can be useful not only for improving real world odor localization, but also for quantitatively characterizing the influence of group size on task performance.

Is the classical two-term approximation of electron kinetic theory satisfactory for swarms and plasmas?

Abstract: The 'two-term' approximation (representation of the electron distribution by the first two terms of an expansion in spherical harmonics in velocity space) continues to occupy a central role in the low-temperature plasma physics literature, in spite of the mass of evidence illustrating its inadequacy in the swarm (free diffusion) limit for many molecular gases. Part of the problem lies in the failure of many authors to specify quantitatively what they mean when they say that the two-term approximation is 'acceptable'. Thus for example, an error of 10% in transport coefficients may well be acceptable in many plasma applications, but for analysis of highly accurate swarm experiments to compare with ab initio and beam-derived cross-sections, 0.1% or less is required, making 'multi-term' analysis mandatory. While reconciliation of the swarm and plasma literature along the lines of two different accuracy regimes may thus be possible, we dispute claims that the two-term approximation is generally satisfactory for inversion of swarm experiment data to obtain electron impact cross-sections. The unsatisfactory nature of other assumptions implicit in much of the modern plasma kinetic theory literature is also discussed.

Visualizing particle swarm optimization - Gaussian particle swarm optimization

Abstract: Particle swarm optimization (PSO) conjures an image of particles searching for the optima the way bees buzz around flowers. One approach at visualizing the swarm graphs where all the particles are each generation, thus demonstrating the random nature associated with swarms of insects. Another approach is to show successive bests, thus showing the way that the swarm progresses. Some have even looked at the specific search path of the particle that eventually finds the optima. These approaches provide limited understanding of PSO. This paper presents a new visualization approach based on the probability distribution of the swarm, thus the random nature of PSO is properly visualized. The visualization allows better understanding of how to tune the algorithm and depicts weaknesses. A new algorithm based on moving the swarm a Gaussian distance from the global and local best is presented. Gaussian particle swarm optimization (GPSO) is compared to PSO.

Swarm aggregations using artificial potentials and sliding mode control

Abstract: In this article we build on results of V. Gazi et al. (2003, 2002) on swarm stability. V. Gazi et al. considered aggregating a swarm model in n-dimensional space based on artificial potential functions for inter-individual interactions and motion along the negative gradient of the combined potential. Here the author considers a general model for vehicle dynamics of each agent (swarm member) and uses sliding mode control theory to force their motion to obey the dynamics of the swarm considered in V. Gazi et al. (2003, 2002). In this context, the results in V. Gazi et al. (2003, 2002) serve as a "proof of concept" for swarm aggregation, whereas the present results serve as a possible implementation method for engineering swarms with given vehicle dynamics. Moreover, the presented control scheme is robust with respect to disturbances and system uncertainties.

SWARM-BOT: from concept to implementation

Abstract: This paper presents a new robotic concept, called SWARM-BOT, based on a swarm of autonomous mobile robots with self-assembling capabilities. SWARM-BOT takes advantage from collective and distributed approaches to ensure robustness to failures and to hard environment conditions in tasks such as navigation, search and transportation in rough terrain. One SWARM-BOT is composed of a number of simpler robots, called s-bots, physically interconnected. The SWARM-BOT is provided with self-assembling and self-reconfiguring capabilities whereby s-bots can connect and disconnect forming large flexible structures. This paper introduces the SWARM-BOT concept and describes its implementation from a mechatronic perspective.

Self-organized motion in anisotropic swarms

Abstract: This paper considers an anisotropic swarm model with a class of attraction and repulsion functions. It is shown that the members of the swarm will aggregate and eventually form a cohesive cluster of finite size around the swarm center. Moreover, It is also proved that under certain conditions, the swarm system can be completely stable, i.e., every solution converges to the equilibrium points of the system. The model and results of this paper extend a recent work on isotropic swarms to more general cases and provide further insight into the effect of the interaction pattern on self-organized motion in a swarm system.

Swarms in dynamic environments

Abstract: Charged particle swarm optimization (CPSO) is well suited to the dynamic search problem since inter-particle repulsion maintains population diversity and good tracking can be achieved with a simple algorithm. This work extends the application of CPSO to the dynamic problem by considering a bi-modal parabolic environment of high spatial and temporal severity. Two types of charged swarms and an adapted neutral swarm are compared for a number of different dynamic environments which include extreme 'needle-inthe-haystack' cases. The results suggest that charged swarms perform best in the extreme cases, but neutral swarms are better optimizers in milder environments.

System, methods and apparatus for integrating behavior-based approach into hybrid control model for use with mobile robotic vehicles

Abstract: Behavior-based models of robotic coordination are integrated into a synthetic hybrid control architecture of a multi-robotic system (MRS) The MRS uses rules to organize the priorities of squads of mobile robotic vehicles (MRVs) in a broader system that includes a central control model for planning, hierarchy and simulations The system, and methods and apparatus thereof, is applied to the organization of the swarm weapon system

Swarm Intelligence: A New C2 Paradigm with an Application to Control Swarms of UAVs

Abstract: : We have developed an agent-based model to simulate command and control of a swarm of Unmanned Air Vehicles (UAVs). Our approach makes use of decentralized strategies to control a UAV swarm carrying out a search mission. In this paper, we introduce our approach, we present the details of the proposed model, and we provide results of simulations testing our control strategies under a variety of configurations. We also outline some initial results obtained by extending our simulation tool to include the ability to carry out missions in which UAVs can track moving targets, strike targets, and perform Battle Damage Assessment.

Studies on Artificial Fish Swarm Optimization Algorithm based on Decomposition and Coordination Techniques

Abstract: In allusion to the characters of the complex large scale systems, such as the excessive equation numbers, too high orders of the variables, etc., an extended artificial fish swarm algorithm based on decomposition and coordination method is proposed. A calculation for a heat exchanger system has been done, and the computation result demonstrate that this technique has some advantages as convergence, insensitive to initial values, insensitive to parameters, and so on.

A new swarm mechanism based on social spiders colonies: from web weaving to region detection

Abstract: In multi-agent systems, the reactive approach emphasizes on the individual simplicity in comparison to the collective complexity of the task being performed. However, to apply such an approach to solve a problem, the components of the multi-agent system have to be designed such as the society is able to fulfill its requirements with a reasonable efficiency. Taking inspiration from natural swarm systems is a way to solve this conception issue.This article presents a new swarm mechanism inspired by the simulation of the collective weaving in social spiders. The main difference from existing mechanisms is the possibility in the spider model to integrate non-local information in local processing. In this paper, we describe the simulation model and its transposition to a specific application case: the extraction of regions in an image. Some experiments conducted on real gray level images are detailed together with studies about the influence of the different algorithm parameters on its performance.

Computational design of swarms

Abstract: In this work, a method for the rapid computational design and simulation of multiparticle swarms is developed. Specifically, a non-convex optimization strategy is constructed, based on genetic algorithms, to design desired swarm-like behaviour. To allow rapid evaluation of various swarm design performances, a temporally-adaptive iterative scheme is developed to determine the positions, velocities and accelerations of members of the swarm. The overall purpose of such an approach is to facilitate rapid decision making for the dynamics of large numbers of interacting objects, whose goal is to reach a target guarded by obstacles in a minimum amount of time. Copyright © 2003 John Wiley & Sons, Ltd.

Agent-Based Verification of von Thünen's Location Theory

Abstract: The spatial pattern as described by von Thunen is considered an optimal solution to maximize society's well-being in a hypothetical environment. We developed a model to demonstrate whether a collection of autonomous individuals can contribute to the formation of this optimal pattern, without any system-level optimization capabilities. We also analyzed the mechanism that leads to an emergent spatial optimization by applying theories of positive feedbacks and lock-in.

Comparing PSO structures to learn the game of checkers from zero knowledge

Abstract: This paper investigates the effectiveness of various particle swarm optimiser structures to learn how to play the game of checkers. Co-evolutionary techniques are used to train the game playing agents. Performance is compared against a player making moves at random. Initial experimental results indicate definite advantages in using certain information sharing structures and swarm size configurations to successfully learn the game of checkers.

Thorough warm-up before take-off in honey bee swarms

Abstract: In a bivouacked swarm of honey bees, most individuals are quiescent while a small minority (the scouts) are active in choosing the swarm's future nest site. This study explores the way in which the members of a swarm warm their flight muscles for take-off when the swarm eventually decamps. An infrared camera was used to measure the thoracic (flight muscle) temperatures of individual bees on the surface of a swarm cluster. These are generally the coolest bees in a swarm. The warming of the surface-layer bees occurred mainly in the last 10 min before take-off. By the time a take-off began, 100% of the bees had their flight muscles heated to at least 35°C, which is sufficient to support rapid flight. Take-offs began only a few seconds after all the surface-layer bees had their flight muscles warmed to at least 35°C, but exactly how take-offs are triggered remains a mystery.

Evolutionary exploration of dynamic swarm behaviour

Abstract: In general, it is difficult to make a highly dynamic swarm system follows explicit behaviour patterns. Multiple, simultaneous interactions among a large number of agents make the non-linear relationship between a parameter change and the corresponding effect on global behaviour non-intuitive and, consequently, hard to control. This paper presents breeding experiments of dynamic swarm behaviour patterns using an interactive evolutionary algorithm. Specifically, eight scalar parameters that influence swarm behaviour dynamics in a 3D swarm simulation are bred to produce agents that collectively fly in line, ring, and figure-eight formations. Our initial examples demonstrate that a 'swarm breeding' system can partly eliminate the manual tuning of control parameters and provides a viable approach to design swarm systems through interactive genetic programming.