Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-08-16T20:20:26Z No. of bitstreams: 1 AtilaVarelaFerreiraMedeirosDeOliveira_DISSERT.pdf: 1603393 bytes, checksum: dca520d8a49b825f11ed063f8807d7f1 (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-08-18T00:33:44Z (GMT) No. of bitstreams: 1 AtilaVarelaFerreiraMedeirosDeOliveira_DISSERT.pdf: 1603393 bytes, checksum: dca520d8a49b825f11ed063f8807d7f1 (MD5) / Made available in DSpace on 2016-08-18T00:33:44Z (GMT). No. of bitstreams: 1 AtilaVarelaFerreiraMedeirosDeOliveira_DISSERT.pdf: 1603393 bytes, checksum: dca520d8a49b825f11ed063f8807d7f1 (MD5) Previous issue date: 2015-12-07 / Este trabalho prop?e uma nova estrat?gia de navega??o aut?noma assistida por algoritmo gen?tico com planejamento din?mico para rob?s m?veis terrestres, chamada DPNA-GA (Dynamic Planning Navigation Algorithm optimized with Genetic Algorithm). A estrat?gia foi aplicada em ambientes - tanto est?ticos, quanto din?micos - nos quais a localiza??o e o formato dos obst?culos n?o s?o previamente conhecidos. A cada evento de deslocamento, uma nova rota ? planejada atrav?s de um algoritmo que minimiza a dist?ncia entre o rob? e o objetivo e maximiza a dist?ncia em rela??o aos obst?culos. Utilizando um sensor de localiza??o espacial e um conjunto de sensores de dist?ncia, a estrat?gia de navega??o proposta foi capaz de planejar dinamicamente percursos ?timos livres de colis?o. Simula??es realizadas em diferentes ambientes demostraram que a t?cnica fornece um alto grau de flexibilidade e robustez. Para isso, foram aplicadas diversas varia??es de par?metros gen?ticos, tais como: taxa de cruzamento, tamanho da popula??o, dentre outros. Finalmente, os resultados das simula??es demonstram satisfatoriamente a efic?cia e robustez da t?cnica DPNA-GA, validando-a para aplica??es reais em rob?s m?veis terrestres. / This work proposes a new autonomous navigation strategy assisted by genetic algorithm with dynamic planning for terrestrial mobile robots, called DPNA-GA (Dynamic Planning Navigation Algorithm optimized with Genetic Algorithm). The strategy was applied in environments - both static and dynamic - in which the location and shape of the obstacles is not known in advance. In each shift event, a control algorithm minimizes the distance between the robot and the object and maximizes the distance from the obstacles, rescheduling the route. Using a spatial location sensor and a set of distance sensors, the proposed navigation strategy is able to dynamically plan optimal collision-free paths. Simulations performed in different environments demonstrated that the technique provides a high degree of flexibility and robustness. For this, there were applied several variations of genetic parameters such as: crossing rate, population size, among others. Finally, the simulation results successfully demonstrate the effectiveness and robustness of DPNA-GA technique, validating it for real applications in terrestrial mobile robots.