Artificial Life with Robotics

Added on - 28 May 2020

  • 13

    pages

  • 2738

    words

  • 2

    views

  • 0

    downloads

Showing pages 1 to 4 of 13 pages
Artificial Lifewith Robotics
Table of ContentsTable of Contents.......................................................................................................................................11.Introduction.......................................................................................................................................22.Literature Survey..............................................................................................................................23.Artificial Life......................................................................................................................................14.DEAPalgorithmin python..............................................................................................................25.Ant food collection genetic problem.................................................................................................36.Implementation and screenshots......................................................................................................47.Motivations.........................................................................................................................................58.Conclusion..........................................................................................................................................59.References..........................................................................................................................................5Appendix....................................................................................................................................................71
AbstractThe objective of the project isimplemented by optimizing the ant foodcollection using DEAP algorithm. Eachposition is estimated with its function. Thegenetic algorithm is used for the objectdetection. Genetic algorithm technology isused as it comes under DEAP algorithm.The implementation is done in python andthe screenshots are provided. Suitablemotivations are made finally.1.IntroductionThe artificial life has boughtdifferent changes in the biological life. Theants of some species wander and find foodand return to their colony. The geneticprogramming (GP), are classified into twotypes: using data sets and another usingenvironment. The Ant colony optimization(ACO) is a population based and to findsolutions to difficult optimization problems.Deap algorithm is a novel evolutionaryframework for rapid prototyping and testingideas. The design from most otherframeworks makes the algorithm explicitand data structure transparent. Deap core hastwo types: The creator is a meta-factoryallows run time creation by inheritance andcomposition. The toolbox is a container fortools and user can use it. It consists of theselected tools by the user.The main objective of the project isto optimize the ant food collection usingDEAP algorithm. Each position will beestimated with its function. The geneticalgorithm will be used for the objectdetection. Genetic algorithm technology willbe used as it comes under DEAP algorithm.The implementation will be done in pythonand the screenshots will be provided.Suitable motivations will be made finally.2.Literature SurveyAccording to[1], artificial life cycle of antsin today world has become more efficientbio-inspired technologies withcombinational optimization problemsdiscovered by Dorrigo, the ant-basedmetaheuristic ability provides ability onsolving many fundamental and practicalproblems. At first it was used to solve theAnt food genetic problem. Dynamic real-2
life problems are more difficult to solve thanthe static ones. Ant Colony System in manyvariants was introduced and introduced alocal updating pheromone rule in order tofavor exploration as a consequence to find abetter local solution. The Ant ColonyOptimization is based in general on the ant’sability on finding the shorter paths betweentheir nest and the food location. Theartificial ants are using the indirectcommunication based on pheromonequantity laid on their trails. As in real life,the ants use the trails with a strongpheromone showing that the most promisingtour is the one with higher amounts ofpheromone. Pharaoh ants are originally fromAfrica and are also calledMonosodiumpharaonic. As a specificcharacteristic, the Pharaoh ant colonies arenot well defined, they are known as“unicolonial”. It is easy to add or removeants on create or remove colonies towhatever size. The results show that 37% ofthe ants make a U-turn and also walk withtheir sting extended. The results indicate abehavioral specialization: several ants arewalking backwards and forwards layingpheromone, for guiding the other ants. It isrequired a continual flow of workers toreplace any pheromone that decays;therefore there are necessary of a largenumber of ants to extend the exploitation.According to [2], DEAP (DistributedEvolutionary Algorithms in Python)algorithm is a computation framework forrapid prototyping and testing of ideas. Thisalgorithm design from most other existingframeworks in that it seeks to makealgorithms explicit and data structurestransparent, as opposed to the more commonblack box type of frameworks. Several OOPtools have been developed for EvolutionaryComputation (EC), for example EO, ECJ,and Open BEAGLE, etc.In the Proposed algorithm our aim is toprovide a toolbox that encourages users towrite their own evolutionary algorithms,explicitly controlling every aspect of theevolutionary process like data types, fitnessmeasures, population initialization,operators, evolutionary loop, etc.3.Artificial LifeArtificial life has the fundamental ofliving system in understanding the complexinformation processing. The artificial lifename is the natural life for recreating the3
desklib-logo
You’re reading a preview
card-image

To View Complete Document

Become a Desklib Library Member.
Subscribe to our plans

Unlock This Document