Local Planning of AUV Based on Fuzzy-Q Learning in Strong Sea Flow Field

Author

Yang, Ge ; Zhang, Rubo ; Xu, Dong ; Zhang, Ziyin

Author_Institution

Sch. of Comput. Sci. & Technol., Harbin Eng. Univ., Harbin, China

Volume

1

fYear

2009

fDate

24-26 April 2009

Firstpage

994

Lastpage

998

Abstract

This article integrated reinforcement learning with fuzzy logic method for AUV local planning under the strong sea flow field. A fuzzy behavior is defined to resist the sea flow by giving a extra angle towards sea flow. And Q-learning is used to adjust the peak point of fuzzy membership function of the resisting sea flow behavior. This behavior is complemented by two other behaviors, the moving-to-goal behavior and collision avoiding behavior. The recommendations of these three behaviors are integrated through adjustable weighting factors to generate the final motion command for the AUV. Simulation shows it improve the adaptability of AUV under different sea flow greatly.

Keywords

collision avoidance; fuzzy logic; fuzzy set theory; learning (artificial intelligence); mobile robots; underwater vehicles; AUV local planning; autonomous underwater vehicles; collision avoiding behavior; fuzzy behavior; fuzzy-Q learning; integrated reinforcement learning; logic method; moving-to-goal behavior; sea flow field; Algorithm design and analysis; Computer science; Fuzzy logic; Learning; Navigation; Optimization methods; Orbital robotics; Resists; Technology planning; Vehicle dynamics; AUV; Fuzzy-Q; local planning; see flow;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Sciences and Optimization, 2009. CSO 2009. International Joint Conference on

Conference_Location

Sanya, Hainan

Print_ISBN

978-0-7695-3605-7

Type

conf

DOI

10.1109/CSO.2009.244

Filename

5193861