SwarmIntelligencePaper

8/7/2019 SwarmIntelligencePaper

1/11

Swarm Intelligence

Jonas Pfeil

Communication and Operating Systems GroupBerlin University of Technology

[email protected]

Abstract. Swarms have fascinating properties. Their individual mem-bers follow simple rules yet the swarm accomplishes complex tasks.No single member controls the swarm, making it extremely robust. Thissimplicity and robustness make them an interesting model for solvingproblems in computer science. In this paper the term swarm intelligence

is explained and the motivation behind the approach is discussed. Proper-ties of swarms and social insects are described and the process of buildinga metaheuristic after an example in nature is looked at. Different usesof swarm intelligence are introduced and the usefulness of the field isevaluated.

1 Introduction and Definition

Swarm intelligence (SI) as defined by Bonabeau, Dorigo and Theraulaz is anyattempt to design algorithms or distributed problem-solving devices inspired bythe collective behavior of social insect colonies and other animal societies [1,p. 7]. So every time something is inspired by swarms it is swarm intelligence.

But why imitate swarms in the first place?Swarms have fascinated scientist for a long time. Insect colonies for exampleseem to work in a coordinated manner yet no single member of the swarm is incontrol. What is accomplished is an emergent phenomenon. Termites build giantstructures, ants manage to find food sources quickly and efficiently and flocks ofbirds and schools of fish fend off predators and move as one body. But how doesnature create this coordination?

This question is discussed in the next section. In Sect. 3 the two existingmetaheuristics inspired by swarms are introduced, while in Sect. 4 other uses ofthe research on swarms are described. The last section evaluates the usefulnessof the approach and summarizes this paper.

2 Swarm Intelligence in Nature

Swarm behavior in nature is divided into two categories: Species whose individ-uals form a swarm because they benefit in some way and social insects whichlive in colonies whose members cannot survive on their own.


2/11

2.1 Social Insects

Compared to the complexity of the buildings and actions of the colony the

relative simplicity of an individual is a striking feature of social insects. Termitesfor example build giant mounds with ventilation shafts and grow fungus fornourishment. Ants manage to efficiently search an area for food whether itis evenly distributed or scattered in patches (see Fig. 1), an example for therobustness of the insect colony. Social insects also efficiently divide tasks likefinding food, feeding the brood and defending the nest.

Fig. 1. Foraging patterns of three army ant species: Eciton hamatum, E. rapaxand E. burchelli. The different patterns are a result of the distribution of foodsources. The food of E. burchelli is evenly distributed while for E. hamatum it isdistributed in patches. E. rapax has an intermediary distribution. After Burtonand Franks [2]. Image taken from [1, p. 37]. Kansas Science Bulletin.

All this is not achieved by central control but by stigmergy 1 and very seldomby one to one communication. Stigmergy describes an indirect communicationby leaving marks in the environment. These marks can be the structures that arebuilt or markers meant especially for the purpose of communication (typically

1 Grasse introduces stigmergy as follows: The coordination of tasks and the regulationof constructions does not depend directly on the workers, but on the constructionsthemselves. The worker does not direct his work, but is guided by it. It is to this spe-cial form of stimulation that we give the name STIGMERGY (stigma, wound froma pointed object; ergon, work, product of labor D stimulating product of labor). [3,p. 65]


3/11

pheromones which can be smelled by the individuals). The marks left by thecolony act as stimuli for the individuals and can trigger certain actions.

While constructing a nest termites for example will start by randomly placingpellets of mud. When there is an aggregation of pellets they will more likely droppellets at that location than elsewhere. In addition the termites are guided bypheromone concentration forming for example the pattern for the royal chamberaround the queen [3].

Ants use pheromones to find shortest paths to food sources. They lay outpheromone trails behind them and prefer regions with higher pheromone con-centration when deciding where to go. Some species deposit different amountsof pheromone depending whether they are on the way to or back from the foodsource and depending on its size. As ants taking the shorter path will reinforcethe trail more often the pheromone concentration rises and the path will be pre-ferred by following individuals (see Fig. 2). This self-energizing effect leads to thedevelopment of a shortest path used by the individuals. Pheromone evaporation

prevents stagnation, allowing for dynamic changes in the environment. It alsoavoids premature convergence on a not optimal path.

(a) (b)

Fig. 2. Ants find the shorter path in an experimental setup. A bridge leads froma nest to a foraging area. (a) 4 minutes after bridge placement. (b) 8 minutesafter bridge placement. After Goss et al. [4].

2.2 Flocks, Herds and Schools

Social insects do not have a choice whether or not to live in swarms but whatare the advantages for herd animals, flocks of birds and schools of fish thatcause the formation of swarms? Defense against predators is thought to be the


4/11

most important reason for animals to join a swarm. As Kenward [5] showed thesuccess of hawk attacks on pigeons decreases greatly with the size of the swarm.Also the disadvantage of sharing food sources can be outweighed by the reducedchances of finding no food at all, whenever the food is unpredictably distributedin patches [6, p. 209]. Individuals may also increase their chances of finding amate [7] and for animals that travel great distances like migratory birds andcertain fish species there is a decrease in energy consumption when moving ina tight formation.

As flocks, herds and schools can become very large and the individuals areboth limited in their mental capacity and their perception, it can be assumedthat only simple, local rules control the movements of a single animal. Localmeans that only objects in a certain neighborhood depending on the perceptionof the individual are taken into account. The most basic behaviors seem to bean urge to stay close to the swarm and one to avoid collisions [7].

The perception is of course not the same for different species resulting in a

different range of possible swarm behaviors. Fish for example cannot see as faras birds especially in murky water but can feel the pressure waves of neighborswith their lateral line organ [8]. Birds on the other hand have long-range visionenabling them to see the movements of far away flock mates. This enables themto prepare for the change of direction, which explains the quick propagationof maneuver waves going through a flock that is much faster than can beexplained by strictly local rules and the reaction times of the birds [ 9].

Computer simulations have been created after these findings. Reynolds [10]created a computer graphics simulation of swarms which he called the boids2

model using three simple local rules for the movement of an individual: Colli-sion avoidance, velocity matching (heading and speed) and flock centering (seeFig. 3). Heppner and Grenander [11] independently developed a similar modelusing stochastic nonlinear differential equations [12].

(a) (b) (c)

Fig. 3. Rules for the boids simulation: (a) Collision avoidance. (b) Velocitymatching. (c) Flock centering. After Reynolds [10].

Swarms in nature could be said to run in constant time because everyindividual interacts only with its neighbors and therefore its mental capacity

2 Boid means bird-oid object. Not necessarily a bird [10].


5/11

does not limit the size of the swarm3. In the simulation the relations to allother indiviuals have to be taken into account at least to determine if they arein the neighborhood. Without further measures like spatial data structures thecomplexity will be O(n2).

3 Metaheuristics

An SI-metaheuristic is an arbitrary problem solving strategy which falls underthe SI-definition. That is, it is inspired by the behavior of social insect coloniesand other animal societies. Currently there exist two different metaheuristics ant colony optimization (ACO) and particle swarm optimization (PSO).

Stochastic diffusion search (SDS) is an optimization technique introduced byBishop in 1989 [14]. His original paper included no reference to nature and it hasnot been included in any of the books about SI [1,15,16]. The only work claimingthat SDS is an SI-algorithm is a paper published in 2006 by Meyer, Nasuto and

Mark [17]. They see many similarities with ant and evolutionary algorithms.As SDS was not inspired by swarms it is doubtful if it can be said to belong tothe SI-field. It is therefore not further discussed in this paper.

3.1 Ant Colony Optimization

Ant colony optimization [18] is a metaheuristic for difficult combinatorial opti-mization problems modeled after the stigmergetic communication of ants findingshortest paths to food sources. The first ACO-algorithm was Ant System (AS),introduced by Dorigo [19] in 1992. He later generalized it into the ACO meta-heuristic. Ant colony optimization uses virtual ants laying out virtual pheromonein the problem states they visit. As in nature the virtual ants communicate indi-rectly and the solution to the problem emerges by the cooperation of the colony.

As an example a simple implementation for the traveling salesman problem(TSP) could work as follows: Ants start at a random city and choose the nextcity stochastically but prefer the road with more pheromone. When they cannotchoose another city or have completed a tour, they die. If they managed tocomplete a tour they deposit pheromone on all the visited edges. The shorterthe tour, the more pheromone is placed. Ants work simultaneously and new antsare created as needed to keep the population on a desired level. The search isfinished when a short enough tour is found, or a maximum number of iterationswere done.

Algorithm 1 shows the metaheuristic in pseudocode. It searches for a short-est path through a problem graph. Ants are created on random problem statesand move around the graph. When selecting a neighbor state the ants make a

stochastic decision guided by the pheromone concentration on the edge, theirprivate information (that is, the previous states) and problem-specific local in-formation. Ants die if they have found a solution or there are no more feasible

3 In nature schools of fish for example can span multiple miles and contain millions offish [13, p. 64].


6/11

states to move to. Depending on the implementation they can deposit pheromoneon the edges while they are moving, when they die or both. When depositingpheromone after a solution is found, the amount can depend on the quality ofthe solution. The algorithm terminates when a satisfying solution was found oranother termination criterion is reached (e.g., a time constraint). Algorithm 1 isa nonparallel version of ACO but generally the ants like in nature can worksimultaneously allowing a parallel implementation.

Algorithm 1 Ant Colony Optimization1: repeat2: if antCount < maxAnts then3: create a new ant4: set initial state5: end if6: for all ants do

7: determine all feasible neighbor states {considering the ants visited states}8: if solution found no feasible neighbor state then9: kill ant

10: if we use delayed pheromone update then11: evaluate solution12: deposit pheromone on all used edges13: end if14: else15: stochastically select a feasible neighbor state {directed by the ants memory,

the pheromone concentration on the edges and local heuristics}16: if we use step-by-step pheromone update then17: deposit pheromone on the used edge18: end if19: end if

20: end for21: evaporate pheromone22: until termination criterion satisfied {e.g., found a satisfying solution}

Dorigo used the TSP as a benchmark problem for Ant System (AS). The re-sults were comparable or even better than those of genetic algorithms and somegeneral purpose heuristics for small problems but degraded for larger problems.A number of improved versions of AS and other algorithms after the ACO meta-heuristic have been created since then [18]. Applications range from sequentialordering problems over vehicle routing and scheduling problems to telecommu-nications networks.

3.2 Particle Swarm Optimization

Particle swarm optimization is a metaheuristic for the optimization of contin-uous functions. It was created by Kennedy and Eberhart [20] in 1995 and was


7/11

inspired by bird flocking behavior. Kennedy and Eberhart originally wanted tosimulate a social system and therefore used the models created by Reynolds[10] and Heppner [11]. Somewhere in the process they realized that a flock ofbirds searching for food could be a good model for the optimization of arbitraryfunctions.

In the algorithm virtual birds fly around the problem space and evaluate thefunction. Each bird remembers its personal best position xpbest (that is, wherethe function was fittest) and of all these, the globally best personal value xgbestis determined. As shown in (1) birds are attracted by xpbest and xgbest. At eachiteration the birds velocity vectors v are modified. An acceleration towards xpbestand xgbest is stochastically calculated. The factor 2 was empirically determined.Each force is given equal measure to ensure a balance between exploration andconvergence. Like with ACO the algorithm terminates when a position withsatisfying fitness was found or another termination criterion is reached.

v = v + 2 rand() (xpbest xpresent) + 2 rand() (xgbest xpresent) (1)

Kennedy and Eberhart called the algorithm particle swarm optimization be-cause it had no longer any features of a flock and the birds where now particles(points with a velocity). It has moved quite far from the natural counterpart butstill resembles the information exchange between individuals in a swarm. In thiscase birds alerting each other to food sources.

Since the introduction of PSO several improvements have been made to thealgorithm, like friction of the particles and adjustments for optimizing dynamicsystems. Applications include human tremor analysis, power system load stabi-lization and product mix optimization [21].

3.3 Comparison to Evolutionary Computation

Swarm intelligence algorithms have strong similarities to evolutionary computa-tion (EC). Both paradigms use agents which are initialized with random values.While in EC and PSO the knowledge about the problem is contained in thecurrent population, in ACO it exists in the form of the virtual pheromone trails.Also in PSO the population is not replaced by a new one generated by recom-bination and mutation but by flying through the problem space and constantlychanging the velocity.

4 Other Uses

4.1 Swarm Robotics

Swarm robotics is the study of robotic systems build by a swarm of robotsinteracting and cooperating to accomplish a set task. Self-organization and self-assembly properties of social insects are tried to be achieved for swarm robots.


8/11

One of the most interesting research projects in the field has been the Swarm-bots project [22]. Its aim was to construct small robots called s-bots which can

join to form a swarm-bot. A swarm-bot is a loose or rigid formation of s-botsthat can pass rough terrain, overcome obstacles like huge gaps (see Fig. 4) andtransport large objects. Actions a single s-bot could not perform.

Fig. 4. Swarm-bot passing over a large gap. Image taken from [23].

Each s-bot has a gripper for connecting to another s-bot. For interactionthey are equipped with sensors like an omnidirectional camera, torque and fric-tion sensors and microphones as well as with lightsources and sound emitters.The neuronal networks for the control of the s-bots were designed by artificialevolution and can manage tasks like the coordinated motion of the swarm-bot,self-assembly, cooperative transport and exploration.

Self-assembly for example works as follows: An s-bot requiring help switcheson red lights alerting s-bots in the proximity, which try to connect to it andswitch on red lights in turn when they succeeded.

Navigation to a target is accomplished by cooperated exploration. When apath is found s-bots will have formed a chain from the start to the target zonewhich can be used as orientation for other s-bots.


9/11

4.2 Art and Simulations

Apart from algorithms and swarm robotics the knowledge about the underly-ing rules of swarm behavior is used to write computer simulations of swarms.Applications are simulations of realistic animal swarms or even human crowdbehavior. An example is the evaluation of the impact of hydraulic structures onfish populations [24] where fish swarming behavior has to be taken into account.

In computer graphics swarm simulations have also become widely used. Forthe Lord of the Rings trilogy [25] Massive [26] has been developed, a softwarewhich animated thousands of agents for the giant battle scenes. Each agenthas an artificial intelligence brain that can select from a collection of possiblemovements depending on external stimuli. Massive has since then been used for alot of projects including motion pictures and commercials [27]. Apart from theserealistic simulations, art projects like SwarmArt [28] use swarm simulations justbecause of their beauty.

5 Conclusion and Outlook

The complexity of an ant colony or the beautiful sight of a large swarm of birdssurprise with the simplicity of the underlying rules.

With ant colony optimization and particle swarm optimization two algo-rithms have been created which can solve difficult computational problems ef-ficiently, while still beeing easy to understand. As there is a wide variety ofswarm behaviors in nature, there is a great chance we will see more algorithmsand systems modeled after social insects and other social animals.

The challenge in designing such systems will be to define the correct rules forthe interaction of the individuals, as it is not immediately evident which rules

lead to the desired behavior of the swarm.Swarm intelligence is a very active and exciting research field. As our techni-

cal systems become increasingly complex, swarm intelligence algorithms whichconsist of many simple parts become more and more useful as a solution todifficult computational problems.

As the algorithms are parallel in nature, they are well adapted for the useon parallel hardware. On coming processor generations which will feature agrowing number of parallel processing units this may lead to very efficientimplementations of these algorithms.

References

1. Bonabeau, E., Dorigo, M., Theraulaz, G.: Swarm Intelligence: From Natural toArtificial Systems. Santa Fe Institute Studies in the Sciences of Complexity. OxfordUniversity Press, New York, NY (1999)

2. Burton, J.L., Franks, N.R.: The foraging ecology of the army ant eciton rapax: Anergonomic enigma? Ecol. Entomol 10 (1985) 131141


10/11

3. Grasse, P.P.: La reconstruction du nid et les coordinations inter-individuelleschez bellicositermes natalensis et cubitermes sp. la theorie de la stigmergie: es-sai dinterpretation du comportement des termites constructeurs. Insectes Sociaux

6 (1959) 41804. Goss, S., Aron, S., Deneubourg, J.L., Pasteels, J.M.: Self-organized shortcuts in

the argentine ant. Naturwissenschaften 76 (1989) 5795815. Kenward, R.E.: Hawks and doves: Factors affecting success and selection in

goshawk attacks on woodpigeons. Journal of Animal Ecology 47(2) (1978) 4494606. Wilson, E.O.: Sociobiology: The New Synthesis. Belknap Press (1975)7. Shaw, E.: Schooling in fishes: Critique and review. In: Development and Evolution

of Behavior. W. H. Freeman and Company, San Francisco (1970) 4524808. Pitcher, T.J., Partridge, B.L., Wardle, C.S.: A blind fish can school. Science

194(4268) (1976) 963965. Available from: http://www.sciencemag.org/cgi/content/abstract/194/4268/963

9. Potts, W.: The chorus line hypothesis of manoeuvre coordination in avianflocks. Nature 309 (1984) 344345. Available from: http://dx.doi.org/10.1038/309344a0

10. Reynolds, C.W.: Flocks, herds and schools: A distributed behavioral model. In:SIGGRAPH 87: Proceedings of the 14th annual conference on Computer graph-ics and interactive techniques, New York, NY, USA, ACM Press (1987) 2534.Available from: http://doi.acm.org/10.1145/37401.37406

11. Heppner, F., Grenander, U.: A stochastic nonlinear model for coordinated birdflocks. In Krasner, S., ed.: Ubiquity of Chaos. AAAS, Washington, DC (1990)

12. Lebar Bajec, I., Zimic, N., Mraz, M.: Simulating flocks on the wing: The fuzzyapproach. Journal of Theoretical Biology 233(2) (2005) 199220

13. Scheffer, V.B.: Spires of Form: Glimpses of Evolution. Harcourt Brace Jovanovich,San Diego (1985)

14. Bishop, J.M.: Stochastic searching networks. In: Proc. 1st IEE Conf. on ArtificialNeural Networks, London (1989) 329331. Available from: http://ieeexplore.ieee.org/iel3/1151/1872/00051986.pdf?arnumber=51986 [cited 2006-08-14]

15. Kennedy, J., Eberhart, R.C.: Swarm Intelligence. Morgan Kaufmann Publishers(2001)

16. Engelbrecht, A.P.: Fundamentals of Computational Swarm Intelligence. JohnWiley & Sons (2006)

17. Meyer, K.D., Nasut, S.J., Bishop, M.: Stochastic diffusion search: Partial functionevaluation in swarm intelligence dynamic optimisation. In Abraham, A., Grosan,C., Ramos, V., eds.: Studies in Computational Intelligence. Volume 31. SpringerVerlag, Germany (2006). Available from: http://www.doc.gold.ac.uk/seminars/Paper/2006%20Swarm%20Intelligence.pdf [cited 2006-08-15]

18. Dorigo, M., Caro, G.D., Gambardella, L.: Ant algorithms for discrete optimization.Artificial Life 5(2) (1999) 137172. Available from: http://citeseer.ist.psu.edu/dorigo98ant.html [cited 2006-08-10]

19. Dorigo, M.: Optimization, Learning and Natural Algorithms. Dip. elettronica,Politecnico di Milano, Milano, Italy (1992)

20. Kennedy, J., Eberhart, R.C.: Particle swarm optimization. In: Proceedings ofIEEE International Conference on Neural Networks. Volume 4., Piscataway, NJ,IEEE Service Center (1995) 19421948. Available from: http://www.engr.iupui.edu/~shi/Coference/psopap4.html [cited 2006-08-09]

21. Eberhart, R.C., Shi, Y.: Particle swarm optimization: Developments, applicationsand resources. In: Proceedings of the 2001 Congress on Evolutionary Computation.
http://www.sciencemag.org/cgi/content/abstract/194/4268/963http://www.sciencemag.org/cgi/content/abstract/194/4268/963http://dx.doi.org/10.1038/309344a0http://dx.doi.org/10.1038/309344a0http://doi.acm.org/10.1145/37401.37406http://ieeexplore.ieee.org/iel3/1151/1872/00051986.pdf?arnumber=51986http://ieeexplore.ieee.org/iel3/1151/1872/00051986.pdf?arnumber=51986http://www.doc.gold.ac.uk/seminars/Paper/2006%20Swarm%20Intelligence.pdfhttp://www.doc.gold.ac.uk/seminars/Paper/2006%20Swarm%20Intelligence.pdfhttp://citeseer.ist.psu.edu/dorigo98ant.htmlhttp://citeseer.ist.psu.edu/dorigo98ant.htmlhttp://www.engr.iupui.edu/~shi/Coference/psopap4.htmlhttp://www.engr.iupui.edu/~shi/Coference/psopap4.htmlhttp://www.engr.iupui.edu/~shi/Coference/psopap4.htmlhttp://www.engr.iupui.edu/~shi/Coference/psopap4.htmlhttp://www.engr.iupui.edu/~shi/Coference/psopap4.htmlhttp://www.engr.iupui.edu/~shi/Coference/psopap4.htmlhttp://citeseer.ist.psu.edu/dorigo98ant.htmlhttp://citeseer.ist.psu.edu/dorigo98ant.htmlhttp://www.doc.gold.ac.uk/seminars/Paper/2006%20Swarm%20Intelligence.pdfhttp://www.doc.gold.ac.uk/seminars/Paper/2006%20Swarm%20Intelligence.pdfhttp://ieeexplore.ieee.org/iel3/1151/1872/00051986.pdf?arnumber=51986http://ieeexplore.ieee.org/iel3/1151/1872/00051986.pdf?arnumber=51986http://doi.acm.org/10.1145/37401.37406http://dx.doi.org/10.1038/309344a0http://dx.doi.org/10.1038/309344a0http://www.sciencemag.org/cgi/content/abstract/194/4268/963http://www.sciencemag.org/cgi/content/abstract/194/4268/963


11/11

Volume 1., Seoul, South Korea (2001) 8186. Available from: http://ieeexplore.ieee.org/iel5/7440/20223/00934374.pdf?arnumber=934374 [cited 2006-08-10]

22. Dorigo, M.: SWARM-BOT: An experiment in swarm robotics. (2005) 192

200. Available from: http://www.swarm-bots.org/dllink.php?id=707&type=documents [cited 2006-08-13]

23. IRIDIA: (Swarm-bots project). Available from: http://www.swarm-bots.org24. Goodwin, R.A., Nestler, J.M., Anderson, J.J., Weber, L.J.: Virtual fish to evaluate

bypass structures for endangered species. In: Proceedings of the 5th InternationalSymposium on Ecohydraulics, Madrid, Spain (2004)

25. Jackson, P.: Lord of the rings. New Line Cinema (2003). Available from: http://www.lordoftherings.net/ [cited 2006-08-15]

26. Massive Software: (Massive). Available from: http://www.massivesoftware.com[cited 2006-08-09]

27. Animal Logic: Big ad (2005). Available from: http://www.animallogic.com/commercials/cub/ [cited 2006-08-09]

28. Boyd, J.E., Hushlak, G., Jacob, C.J.: SwarmArt: Interactive art from swarm in-telligence. In: MULTIMEDIA 04: Proceedings of the 12th annual ACM interna-tional conference on Multimedia, New York, NY, USA, ACM Press (2004) 628635.Available from: http://doi.acm.org/10.1145/1027527.1027674
http://ieeexplore.ieee.org/iel5/7440/20223/00934374.pdf?arnumber=934374http://ieeexplore.ieee.org/iel5/7440/20223/00934374.pdf?arnumber=934374http://www.swarm-bots.org/dllink.php?id=707&type=documentshttp://www.swarm-bots.org/dllink.php?id=707&type=documentshttp://www.swarm-bots.org/http://www.lordoftherings.net/http://www.lordoftherings.net/http://www.massivesoftware.com/http://www.animallogic.com/commercials/cub/http://www.animallogic.com/commercials/cub/http://doi.acm.org/10.1145/1027527.1027674http://doi.acm.org/10.1145/1027527.1027674http://www.animallogic.com/commercials/cub/http://www.animallogic.com/commercials/cub/http://www.massivesoftware.com/http://www.lordoftherings.net/http://www.lordoftherings.net/http://www.swarm-bots.org/http://www.swarm-bots.org/dllink.php?id=707&type=documentshttp://www.swarm-bots.org/dllink.php?id=707&type=documentshttp://ieeexplore.ieee.org/iel5/7440/20223/00934374.pdf?arnumber=934374http://ieeexplore.ieee.org/iel5/7440/20223/00934374.pdf?arnumber=934374

Documents

SwarmIntelligencePaper