Distributed fuzzy discrete event system for robotic sensory information processing |
| |
Authors: | Rajibul Huq George KI Mann Raymond G Gosine |
| |
Affiliation: | C-CORE and Faculty of Engineering, Memorial University of Newfoundland, St John's, Newfoundland, Canada E-mail: |
| |
Abstract: | Abstract: This paper presents a novel intelligent sensory information processing technique using a fuzzy discrete event system (FDES) for robotic control. The proposed method combines the predictive control approach of a discrete event system with the approximate reasoning aspect of fuzzy logic. It develops a supervisory control strategy for behavior-based robotic control using distributed FDES. The application of distributed FDES eliminates the formation of complex fuzzy predicates and a large fuzzy rule-base. The FDES-based approach also provides means for analyzing behavior-based decision-making using the observability and controllability of an FDES. The observability of an FDES describes uncertainties in sensory data, and the controllability of an FDES exploits uncertain state transitions in a dynamic environment. Comprehensive experiments on behavior-based mobile robot navigation are presented to authenticate the performance of the proposed methodology. |
| |
Keywords: | fuzzy discrete event system behavior-based robotic control discrete event system fuzzy logic supervisory control mobile robot navigation |
|