Robótica evolutiva aplicada ao problema de perseguição-evasão de pior caso com múltiplos robôs

• Ano de defesa: 2016
• Autor(a) principal: Gregorin, Livia do Vale
• Orientador(a): Freire, Eduardo Oliveira
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Sergipe
• Programa de Pós-Graduação: Pós-Graduação em Engenharia Elétrica
• País: Brasil
• Palavras-chave em Português: Engenharia elétrica; Robótica; Máquinas; Robótica evolutiva; Perseguição-evasão; Problema de limpeza
• Área do conhecimento CNPq: ENGENHARIAS::ENGENHARIA ELETRICA
• Link de acesso: https://ri.ufs.br/handle/riufs/5032

Over the years,there is a growing demand for the use of robots toassis thu mans in their tasks, especially those involving risks,such as search and rescue. For this reason, coordination amongs everal robots has been acommonoption,and one of the ways to study and model these applications involves the problem of pursuit-evasion. This work proposes the use of an evolutionary robotics approach to solve the worst-case pursuit- evasion problem, in which evaders are considered arbitrarily fast and omniscient, while pursuers have limited sensing and communication capabilities. In this research,no prior knowledge is considered regarding environments, which retreated as discrete and canbe multiply connected. A decentralized multi-robot control system is proposed, based on a nite state machine with state-action mapping de ned by means of a genetic algorithm, applied in terms of evolutionary robotics. There sults show the proposed system is able to decontaminate several typesof maps, but does not generalize to all initial conditions,due to the incompleteness in the automaton mapping.Therefore, a complementary approach is presented in which draws a reused alternatively with the evolved automaton, indicating random actions in cases of states not su ciently visited during evolution. This investigation led to better results, indicating ways for future work.Ina ddition, a comparative analysis of the evolutionary approach is also carried out with another solution method for the same problem, with advantages and disadvantages of each work being discussed.