Cooperative Autonomous Agents Based on Dynamical Fuzzy Cognitive Maps
This work presents an architecture for cooperative autonomous agents based on dynamic fuzzy cognitive maps (DFCM) that are an evolution of fuzzy cognitive maps. This architecture is used to build an autonomous navigation system for mobile robotics that pr
- PDF / 1,064,112 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 83 Downloads / 207 Views
Cooperative Autonomous Agents Based on Dynamical Fuzzy Cognitive Maps Márcio Mendonça, Lúcia Valéria Ramos de Arruda and Flávio Neves-Jr
Abstract This work presents an architecture for cooperative autonomous agents based on dynamic fuzzy cognitive maps (DFCM) that are an evolution of fuzzy cognitive maps. This architecture is used to build an autonomous navigation system for mobile robotics that presents learning capacity, on line tuning, self-adaptation abilities and behaviors management. The developed navigation system adopts a multi-agent approach, inspired on the Brooks’ subsumption architecture due to its hierarchical management functions, parallel processing and direct mapping from situation to action. In this paper, a DFCM is hierarchically developed, from low-level describing reactive actions to the highest level that comprises management actions. A multi-agent scheme to share experiences among robots is also implemented at the last hierarchy level based on pheromone exchange by ant colony algorithm. The proposed architecture is validated on a simple example of swarm robotics.
Electronic supplementary material The online version of this article (doi: 10.1007/978-3642-39739-4_10) contains supplementary material, which is available to authorized users. M. Mendonça (B) Federal University of Technology—Paraná UTFPR, Av Alberto Carazzai 1640, Cornélio Procópio, Brazil e-mail: [email protected] L. V. R. Arruda · F. Neves-Jr Federal University of Technology—Paraná UTFPR, Av Sete de Setembro, Curitiba, PR3165, Brazil e-mail: [email protected] F. Neves-Jr e-mail: [email protected] E. I. Papageorgiou (ed.), Fuzzy Cognitive Maps for Applied Sciences and Engineering, Intelligent Systems Reference Library 54, DOI: 10.1007/978-3-642-39739-4_10, © Springer-Verlag Berlin Heidelberg 2014
159
160
M. Mendonça et al.
1 Introduction In mobile robots, the use of computational intelligence techniques such as neural networks, fuzzy logic, evolutionary algorithms or agents is currently. Among these techniques, the intelligent agents can be highlighted. According to Wooldridge and Jennings [15] an “agent” is defined to be a computer system that is assigned to an environment and it is able to decide and take actions in this environment, without external interference, in order to complete the tasks delegated to it. If the environment suffers sudden and unpredictable changes, an ability to learn is particularly important to the agent. Moreover, the coexistence with other agents in the same environment (that characterizes multi-agent systems) with the same or different tasks requires individual and/or group ability to cooperative solve conflicts and reach objectives. In multi-agent systems, the term “collective intelligence” refers to sophisticated collective behaviors that can arise from a combination of many agents with relatively simple behavior and action, each operating autonomously. The development of robotic systems with collective intelligence is a new research area named as Swarm Robotics [13]. In fact, Swarm R
Data Loading...
