Back to Search Start Over

Route evaluation for unmanned aerial vehicle based on type-2 fuzzy sets.

Authors :
Sun, Xixia
Cai, Chao
Yang, Jie
Shen, Xubang
Source :
Engineering Applications of Artificial Intelligence. Mar2015, Vol. 39, p132-145. 14p.
Publication Year :
2015

Abstract

Until now, routes evaluation for unmanned aerial vehicle still faces a variety of difficulties, which is due to the fact that during route evaluating, subjective judgments, quantitative data, and random information need to be considered simultaneously. In this paper, by formulating route evaluation as a multi-criteria decision making problem including uncertainties, an integrated route evaluation approach based on type-2 fuzzy sets is proposed. Firstly, a systemic evaluation framework that incorporates models for scoring evaluation criteria is proposed. Specifically, a survivability model incorporating dynamics and uncertainties in battlefield is developed, including some special features, such as calculating the probability of detecting, tracking, and destroying an unmanned aerial vehicle, and modeling the location of pop-up threats as a Markov chain. Then, type-2 fuzzy sets are introduced to represent linguistic values, managing linguistic uncertainty effectively and making the evaluation process realistic and reliable. Finally, the architecture of perceptual computer is extended, and the computing with words engine by means of linguistic weighted average method is adopted to obtain the overall score of each route, enabling both random and fuzzy uncertainties existing universally in the data to be effectively managed in a unified format. The proposed method has the advantages of diverse inputs such as numbers, probability distributions and words. All these can be aggregated to a final decision. Furthermore, it provides a useful tool to handle route evaluation problem in a highly reliable and intelligent manner, and it can be applied to solve multi-criteria decision making problems in many disciplines. Experimental results demonstrate the feasibility and effectiveness of our method. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
09521976
Volume :
39
Database :
Academic Search Index
Journal :
Engineering Applications of Artificial Intelligence
Publication Type :
Academic Journal
Accession number :
100796917
Full Text :
https://doi.org/10.1016/j.engappai.2014.11.008