The focus of this thesis is on Actual Entities, a concept created by the philosopher Alfred North Whitehead, and how the concept can be applied to Unmanned Aerial Vehicles as a behavioral control method. Actual Entities are vector based, atomic units that use a method called prehension to observe their environment and react with various actions. When combining multiple Actual Entities a Colony of Prehending Entities is created; when observing their prehensions an intelligent behavior emerges. By applying the characteristics of Actual Entities to Unmanned Aerial Vehicles, specifically in a situation where they are searching for targets, this emergent, intelligent behavior can be seen as they search a designated area and locate specified targets. They will alter their movements based on the prehensions of the environment, surrounding Unmanned Aerial Vehicles, and targets.

[pt] O algoritmo de otimização por enxame de partículas (PSO, do inglês Particle Swarm Optimization) é uma meta-heurística baseada em populações de indivíduos na qual os candidatos à solução evoluem através da simulação de um modelo simplificado de adaptação social. Juntando robustez, eficiência e simplicidade, o PSO tem adquirido grande popularidade. São reportadas muitas aplicações bem-sucedidas do PSO nas quais este algoritmo demonstrou ter vantagens sobre outras meta-heurísticas bem estabelecidas baseadas em populações de indivíduos. Algoritmos modificados de PSO já foram propostos para resolver problemas de otimização com restrições de domínio, lineares e não lineares. A grande maioria desses algoritmos utilizam métodos de penalização, que possuem, em geral, inúmeras limitações, como por exemplo: (i) cuidado adicional ao se determinar a penalidade apropriada para cada problema, pois deve-se manter o equilíbrio entre a obtenção de soluções válidas e a busca pelo ótimo; (ii) supõem que todas as soluções devem ser avaliadas. Outros algoritmos que utilizam otimização multi-objetivo para tratar problemas restritos enfrentam o problema de não haver garantia de se encontrar soluções válidas. Os algoritmos PSO propostos até hoje que lidam com restrições, de forma a garantir soluções válidas utilizando operadores de viabilidade de soluções e de forma a não necessitar de avaliação de soluções inválidas, ou somente tratam restrições de domínio controlando a velocidade de deslocamento de partículas no enxame, ou o fazem de forma ineficiente, reinicializando aleatoriamente cada partícula inválida do enxame, o que pode tornar inviável a otimização de determinados problemas. Este trabalho apresenta um novo algoritmo de otimização por enxame de partículas, denominado PSO+, capaz de resolver problemas com restrições lineares e não lineares de forma a solucionar essas deficiências. A modelagem do algoritmo agrega seis diferentes capacidades para resolver problemas de otimização com restrições: (i) redirecionamento aritmético de validade de partículas; (ii) dois enxames de partículas, onde cada enxame tem um papel específico na otimização do problema; (iii) um novo método de atualização de partículas para inserir diversidade no enxame e melhorar a cobertura do espaço de busca, permitindo que a borda do espaço de busca válido seja devidamente explorada – o que é especialmente conveniente quando o problema a ser otimizado envolve restrições ativas no ótimo ou próximas do ótimo; (iv) duas heurísticas de criação da população inicial do enxame com o objetivo de acelerar a inicialização das partículas, facilitar a geração da população inicial válida e garantir diversidade no ponto de partida do processo de otimização; (v) topologia de vizinhança, denominada vizinhança de agrupamento aleatório coordenado para minimizar o problema de convergência prematura da otimização; (vi) módulo de transformação de restrições de igualdade em restrições de desigualdade. O algoritmo foi testado em vinte e quatro funções benchmarks – criadas e propostas em uma competição de algoritmos de otimização –, assim como em um problema real de otimização de alocação de poços em um reservatório de petróleo. Os resultados experimentais mostram que o novo algoritmo é competitivo, uma vez que aumenta a eficiência do PSO e a velocidade de convergência. / [en] The Particle Swarm Optimization (PSO) algorithm is a metaheuristic based on populations of individuals in which solution candidates evolve through simulation of a simplified model of social adaptation. By aggregating robustness, efficiency and simplicity, PSO has gained great popularity. Many successful applications of PSO are reported in which this algorithm has demonstrated advantages over other well-established metaheuristics based on populations of individuals. Modified PSO algorithms have been proposed to solve optimization problems with domain, linear and nonlinear constraints; The great majority of these algorithms make use of penalty methods, which have, in general, numerous limitations, such as: (i) additional care in defining the appropriate penalty for each problem, since a balance must be maintained between obtaining valid solutions and the searching for an optimal solution; (ii) they assume all solutions must be evaluated. Other algorithms that use multi-objective optimization to deal with constrained problems face the problem of not being able to guarantee finding feasible solutions. The proposed PSO algorithms up to this date that deal with constraints, in order to guarantee valid solutions using feasibility operators and not requiring the evaluation of infeasible solutions, only treat domain constraints by controlling the velocity of particle displacement in the swarm, or do so inefficiently by randomly resetting each infeasible particle, which may make it infeasible to optimize certain problems. This work presents a new particle swarm optimization algorithm, called PSO+, capable of solving problems with linear and nonlinear constraints in order to solve these deficiencies. The modeling of the algorithm has added six different capabilities to solve constrained optimization problems: (i) arithmetic redirection to ensure particle feasibility; (ii) two particle swarms, where each swarm has a specific role in the optimization the problem; (iii) a new particle updating method to insert diversity into the swarm and improve the coverage of the search space, allowing its edges to be properly exploited – which is especially convenient when the problem to be optimized involves active constraints at the optimum solution; (iv) two heuristics to initialize the swarm in order to accelerate and facilitate the initialization of the feasible initial population and guarantee diversity at the starting point of the optimization process; (v) neighborhood topology, called coordinated random clusters neighborhood to minimize optimization premature convergence problem; (vi) transformation of equality constraints into inequality constraints. The algorithm was tested for twenty-four benchmark functions – created and proposed for an optimization competition – as well as in a real optimization problem of well allocation in an oil reservoir. The experimental results show that the new algorithm is competitive, since it increases the efficiency of the PSO and the speed of convergence.

Submitted by Maria Aparecida (cidazen@gmail.com) on 2017-04-17T12:23:49Z No. of bitstreams: 1 Tiago Martins Ribeiro.pdf: 2146814 bytes, checksum: c04c7e63303157b4345d0985576e1620 (MD5) / Made available in DSpace on 2017-04-17T12:23:49Z (GMT). No. of bitstreams: 1 Tiago Martins Ribeiro.pdf: 2146814 bytes, checksum: c04c7e63303157b4345d0985576e1620 (MD5) Previous issue date: 2017-02-20 / CAPES / Complex optimization problems have been studied over the years by researchers seeking better solutions, these studies have encouraged the development of several algorithms of artificial intelligence, and a part of them are bio-inspired methods, based on the behavior of populations. These algorithms target to develop techniques based on nature in search of solutions to these problems. In this work, was introduced as a purpose, an algorithm based on the behavior of locust swarms, the Locust Swarm Optimizer (LSO). The behavior of the desert locust is introduced highlighting the formation of clouds of attacks caused by a synthesized neurotransmitter monoamine, present on the insect, known as serotonin. Observing this behavior, the LSO was developed. It was compared to other known artificial intelligence techniques through 23 benchmark functions and also tested on an power system economical dispatch problem. From the point of view of the results and the ease of implementation, it can be concluded that the LSO algorithm is very competitive as compared to existing methods / Problemas complexos de otimização vêm sendo estudados ao longo dos anos por pesquisadores que buscam melhores soluções, estes estudos incentivaram o desenvolvimento de vários algoritmos de inteligência artificial, sendo que uma parte deles são métodos bioinspirados, baseados no comportamento de populações. Estes algoritmos têm como objetivo desenvolver técnicas baseadas na natureza em busca de soluções para estes problemas. Neste trabalho um algoritmo baseado no comportamento de enxames de gafanhotos-do-deserto, o Locust Swarm Optimizer (LSO), foi introduzido como objetivo. O comportamento do gafanhoto-do-deserto é apresentado destacando a formação de nuvens de ataques causada por uma monoamina neurotransmissora sintetizada, presente no inseto, conhecido por serotonina. Observando este comportamento, foi desenvolvido o LSO. Ele foi comparado com outras conhecidas técnicas de inteligência artificial através de 23 funções benchmarks e também, testado em um problema de despacho econômico. Do ponto de vista dos resultados e da facilidade de implementação, pode-se concluir que o algoritmo LSO é bastante competitivo comparado aos métodos atuais existentes.

Ant colony optimization (ACO) is an algorithm which simulates ant foraging behavior. When ants search for food they leave pheromone trails to tell other ants which paths to take to find food. ACO has been adapted to many different problems in computer science: mainly variations on shortest path algorithms for graphs and networks. ACO can be adapted to work as a form of communication between separate agents in a video game AI. By controlling the effectiveness of this communication, the difficulty of the game should be able to be controlled. Experimentation has shown that ACO works effectively as a form of communication between agents and supports that ACO is an effective form of difficulty control. However, further experimentation is needed to definitively show that ACO is effective at controlling difficulty and to show that it will also work in a large scale system.

Swarm robotics for music is a relatively new way to explore algorithmic composition as well as new modes of human robot interaction. This work outlines a strategy for making music with a robotic swarm constrained by acoustic sound, rhythmic music using sequencers, motion causing changes in the music, and finally human and swarm interaction. Two novel simulation programs are created in this thesis: the first is a multi-agent simulation designed to explore suitable parameters for motion to music mappings as well as parameters for real time interaction. The second is a boid-based robotic swarm simulation that adheres to the constraints established, using derived parameters from the multi-agent simulation: orientation, number of neighbors, and speed. In addition, five interaction modes are created that vary along an axis of direct and indirect forms of human control over the swarm motion. The mappings and interaction modes of the swarm robot simulation are evaluated in a user study involving music technology students. The purpose of the study is to determine the legibility of the motion to musical mappings and evaluate user preferences for the mappings and modes of interaction in problem solving and in open-ended contexts. The findings suggest that typical users of a swarm robot system do not necessarily prefer more inherently legible mappings in open-ended contexts. Users prefer direct and intermediate modes of interaction in problem solving scenarios, but favor intermediate modes of interaction in open-ended ones. The results from this study will be used in the design and development of a new swarm robotic system for music that can be used in both contexts.

Cooperation in self-organized heterogeneous swarms is a phenomenon from nature with many applications in autonomous robots. I specifically analyzed the problem of auto-regulated team formation in multi-agent systems and several strategies to learn socially how to make multi-objective decisions. To this end I proposed new multi-objective ranking relations and analyzed their properties theoretically and within multi-objective metaheuristics. The results showed that simple decision mechanism suffice to build effective teams of heterogeneous agents and that diversity in groups is not a problem but can increase the efficiency of multi-agent systems.

M.Sc. University of KwaZulu-Natal, Durban 2013.

Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / ENGLISH ABSTRACT: Swarm intelligence research was inspired by biological systems in nature. Working ants and bees has captivated researchers for centuries, with the ant playing a major role in shaping the future of robotic swarm applications. The ants foraging activity can be adapted for different applications of robotic swarm intelligence. Numerous researchers have conducted theoretical analysis and experiments on the ants foraging activities and communication styles. Combining this information with modern reconfigurable computing opens the door to more complex behaviour with improved system dynamics. Reconfigurable computing has numerous applications in swarm intelligence such as true hardware parallel processing, dynamic power save algorithms and dynamic peripheral changes to the CPU core. In this research a brief study is made of swarm intelligence and its applications. The ants' foraging activities were studied in greater detail with the emphasis on a layered control system designed implementation in a robotic agent. The robotic agent’s hardware was designed using a partial self reconfigurable FPGA as the main building element. The hardware was designed with the emphasis on system flexibility for swarm application drawing attention to power reduction and battery life. All of this was packaged into a differential drive chassis designed specifically for this project. / AFRIKAANSE OPSOMMING: Die motivering vir swerm robotika kom van die natuur. Vir eeue fassineer swerm insekte soos bye en miere navorsers. Dit is verstommend hoe ’n groep klein en nietige insekte sulke groot take kan verrig. Die mier speel ‘n belangrike rol en is die sentrale tema van menige publikasies. Die mier se kos-soek aktiwiteit kan aangepas word vir swerm robotika toepassings. Hierdie aktiwiteit vervat verskeie sleutel konsepte wat belangrik is vir robotika toepassings. Deur bv. die mier se aktiwiteite te kombineer met dinamies herkonfigureerbare hardeware, kan meer komplekse gedrag bestudeer word. Die stelsel dinamika verbeter ook, aangesien dit nou moontlik is om sekere take in parallel uit te voer. Deur ’n interne prosesseerder in die herkonfigureerbare hardeware in te sluit, is dit nou vir die stelsel moontlik om homself te verander tydens taak verrigting. Komplekse krag bestuur gedrag is ook moontlik deurdat die prosesseerder die spoed en rand apparaat kan verander soos benodig. ‘n Verdere voordeel is dat die stelsel aanpasbaar is en dus vir verskeie navorsingsprojekte gebruik kan word. In hierdie navorsing word ’n literatuur studie van swerm robotika gemaak en word daar ook na toepassings gekyk. Met die klem op praktiese implementering, word die mier se kos-soek aktiwiteit in detail ondersoek deur gebruik te maak van ’n laag beheerstelsel. In hierdie laag beheerstelsel verteenwoordig elke laag ’n hoër vlak gedrag. Stelsel aanpasbaarheid en lae kragverbruik speel ’n deurslaggewende rol in die ontwerp, en om hierdie rede vorm ’n FPGA die hart van die sisteem.

A Inteligência de Enxame foi proposta a partir da observação do comportamento social de espécies de insetos, pássaros e peixes. A ideia central deste comportamento coletivo é executar uma tarefa complexa decompondo-a em tarefas simples, que são facilmente executadas pelos indivíduos do enxame. A realização coordenada destas tarefas simples, respeitando uma proporção pré-definida de execução, permite a realização da tarefa complexa. O problema de alocação de tarefas surge da necessidade de alocar as tarefas aos indivíduos de modo coordenado, permitindo o gerenciamento do enxame. A alocação de tarefas é um processo dinâmico pois precisa ser continuamente ajustado em resposta a alterações no ambiente, na configuração do enxame e/ou no desempenho do mesmo. A robótica de enxame surge deste contexto de cooperação coletiva, ampliada à robôs reais. Nesta abordagem, problemas complexos são resolvidos pela realização de tarefas complexas por enxames de robôs simples, com capacidade de processamento e comunicação limitada. Objetivando obter flexibilidade e confiabilidade, a alocação deve emergir como resultado de um processo distribuído. Com a descentralização do problema e o aumento do número de robôs no enxame, o processo de alocação adquire uma elevada complexidade. Desta forma, o problema de alocação de tarefas pode ser caracterizado como um processo de otimização que aloca as tarefas aos robôs, de modo que a proporção desejada seja atendida no momento em que o processo de otimização encontre a solução desejada. Nesta dissertação, são propostos dois algoritmos que seguem abordagens distintas ao problema de alocação dinâmica de tarefas, sendo uma local e a outra global. O algoritmo para alocação dinâmica de tarefas com abordagem local (ADTL) atualiza a alocação de tarefa de cada robô a partir de uma avaliação determinística do conhecimento atual que este possui sobre as tarefas alocadas aos demais robôs do enxame. O algoritmo para alocação dinâmica de tarefas com abordagem global (ADTG) atualiza a alocação de tarefas do enxame com base no algoritmo de otimização PSO (Particle swarm optimization). No ADTG, cada robô possui uma possível solução para a alocação do enxame que é continuamente atualizada através da troca de informação entre os robôs. As alocações são avaliadas quanto a sua aptidão em atender à proporção-objetivo. Quando é identificada a alocação de maior aptidão no enxame, todos os robôs do enxame são alocados para as tarefas definidas por esta alocação. Os algoritmos propostos foram implementados em enxames com diferentes arranjos de robôs reais demonstrando sua eficiência e eficácia, atestados pelos resultados obtidos. / Swarm Intelligence has been proposed based on the observation of social behavior of insect species, birds and fishes. The main idea of this collective behavior is to perform a complex task decomposing it into many simple tasks, that can be easily performed by individuals of the swarm. Coordinated realization of these simple tasks while adhering to a pre-defined distribution of execution, allows for the achievement of the original complex task. The problem of task allocation arises from the need of assigning tasks to individuals in a coordinated fashion, allowing a good management of the swarm. Task allocation is a dynamic process because it requires a continuous adjustment in response to changes in the environment, the swarm configuration and/or the performance of the swarm. Swarm robotics emerges from this context of collective cooperation applied to swarms of real robots. In this approach, complex problems are solved by performing complex tasks using swarms of simple robots, with a limited processing and communication capabilities. Aiming at achieving flexibility and reliability, the allocation should emerge as a result of a distributed process. With the decentralization of the problem and the increasing number of robots in the swarm, the allocation process acquires a high complexity. Thus, the problem of task allocation can be characterized as an optimization process that assigns tasks to robots, so that the desired proportion is met at the end of the optimization process, find the desired solution. In this dissertation, we propose two algorithms that follow different to the problem of dynamic task allocation approaches: one is local and the other global. The algorithm for dynamic allocation of tasks with a local approach (ADTL) updates the task assignment of each robot based on a deterministic assessment of the current knowledge it has so far about the tasks allocated to the other robots of the swarm. The algorithm for dynamic task allocation with a global approach (ADTG) updates the allocation of tasks based on a swarm optimization process, inspired by PSO (Particle swarm optimization). In ADTG, each robot has a possible solution to the swarm allocation, which is continuously updated through the exchange of information between the robots. The allocations are evaluated for their fitness in meeting the goal proportion. When the allocation of highest fitness in the swarm is identified, all robots of the swarm are allocated to the tasks defined by this allocation. The proposed algorithms were implemented on swarms of different arrangements of real robots demonstrating their efficacy, robustness and efficiency, certified by obtained the results.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Os Sistemas Multi-Robôs proporcionam vantagens sobre um robô individual, quando da realização de uma tarefa com maiores velocidade, precisão e tolerância a falhas. Os estudos dos comportamentos sociais na natureza têm permitido desenvolver algoritmos bio-inspirados úteis na área da robótica de enxame. Seguindo instruções simples e repetitivas, grupos de robôs, fisicamente limitados, conseguem solucionar problemas complexos. Quando existem duas ou mais tarefas a serem realizadas e o conjunto de robôs é heterogêneo, é possível agrupá-los de acordo com as funcionalidades neles disponíveis. No caso em que o conjunto de robôs é homogêneo, o agrupamento pode ser realizado considerando a posição relativa do robô em relação a uma tarefa ou acrescentando alguma característica distintiva. Nesta dissertação, é proposta uma técnica de clusterização espacial baseada simplesmente na comunicação local de robôs. Por meio de troca de mensagens entre os robôs vizinhos, esta técnica permite formar grupos de robôs espacialmente próximos sem precisar movimentar os robôs. Baseando-se nos métodos de clusterização de fichas, a técnica proposta emprega a noção de fichas virtuais, que são chamadas de cargas, sendo que uma carga pode ser estática ou dinâmica. Se uma carga é estática permite determinar a classe à qual um robô pertence. Dependendo da quantidade e do peso das cargas disponíveis no sistema, os robôs intercambiam informações até alcançar uma disposição homogênea de cargas. Quando as cargas se tornam estacionárias, é calculada uma densidade que permite guiar aquelas que estão ainda em movimento. Durante as experiências, foi observado visualmente que as cargas com maior peso acabam se agrupando primeiro enquanto aquelas com menor peso continuam se deslocando no enxame, até que estas cargas formem faixas de densidades diferenciadas para cada classe, alcançando assim o objetivo final que é a clusterização dos robôs. / Multi-Robots Systems provide advantages over a single robot when performing a task, achieving a greater speed, higher accuracy and better fault tolerance. The studies of social behavior in nature have allowed to develop bio-inspired algorithms useful in swarm robotics. Following simple and repetitive rules, groups of robots can provide solutions to complex problems. When two or more tasks to be executed by a set of heterogeneous robots, it is possible to cluster the robots according to their intrinsic features. When homogeneous robots are used, the clustering may be achieved by considering the robot relative position regarding the location where the task has to be performed or adding some other distinct feature. In this dissertation, a technique for spatial clustering simply based on local communication between robots is proposed. Through the message exchange between neighboring robots, this technique allows cluster formation without robot movement. Based on the token clustering methods, the proposed technique employs a virtual token, which is called a load. The load allows identifying the class to which a robot belongs. Depending on the amount and weight of the loads available in the system, the robots interchange information to achieve uniform load distribution. When the loads become stationaries, a density is calculated as to guide the remaining loads that are still in motion. As a consequence, the loads of higher weight cluster first and the those of lower weight continue shifting through the swarm, until they start forming different density ranges for each class, thereby achieving the final aim which is robot clustering.