Mapas cognitivos fuzzy dinâmicos aplicados em vida artificial e robótica de enxame
This dissertation proposes the use of Dynamic Fuzzy Cognitive Maps (DFCM), an evolution of Fuzzy Cognitive Maps (FCM), for the development of autonomous system to decision-taking. The FCM represents knowledge in a symbolic way, through concepts and causal relationships disposed in a graph. In its st...
| Autor principal: | Chrun, Ivan Rossato |
|---|---|
| Formato: | Dissertação |
| Idioma: | Português |
| Publicado em: |
Universidade Tecnológica Federal do Paraná
2017
|
| Assuntos: | |
| Acesso em linha: |
http://repositorio.utfpr.edu.br/jspui/handle/1/2512 |
| Tags: |
Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
|
| Resumo: |
This dissertation proposes the use of Dynamic Fuzzy Cognitive Maps (DFCM), an evolution of Fuzzy Cognitive Maps (FCM), for the development of autonomous system to decision-taking. The FCM represents knowledge in a symbolic way, through concepts and causal relationships disposed in a graph. In its standard form, the FCMs are limited to the development of static models, in other words, classical FCMs are inappropriate for development of temporal or dynamic models due to the simultaneous occurrence of all causalities in a permanent structure, i.e., the concepts and the causal relationships are time-invariant. The DFCM uses the same mathematical formalism of the FCM, adding features to its predecessor, such as self-adaptation by means of machine learning algorithms and the possibility of inclusion of new types of concepts and causal relationships into the classical FCM model. From these inclusions, it is possible to develop DFCM models for dynamic decision-making problems, which are needed to the development of intelligent tools in engineering and other correlated areas, specifically, the construction of autonomous systems applied in Autonomous Robotic. In particular, to the areas of Swarm Robotics and Artificial Life, as approached in this research. The developed autonomous system deals with multi-objective problems (such as deviate from obstacle, collect target or feed, explore the environment), hierarchizing the actions needed to reach them, through the use of an architecture for planning, inspired by the Brook’s classical Subsumption model, and a state machine for the management of the actions. Learning machine algorithms, in particular Reinforcement Learning, are implemented in the DFCM to dynamically tune the causalities, enabling the controller to handle not modelled event a priori. The proposed DFCM model is validated by means of simulated experiments applied in the aforementioned areas. |
|---|