A Fuzzy-Q Method to Improve the Adaptability of AUV in Variable Ocean Current Environment
Yang Ge, Rubo Zhang, Dong Xu · 2009
It is very difficult to keep AUV following the planned routes during the AUVpsilas navigation under the strong ocean current. This article integrated Q-learning with fuzzy logic, which makes AUV can resist the influence of ocean current. A fuzzy behavior is defined to resist the ocean current by giving a extra angle towards its direction. And Q-learning is used to adjust the central point of fuzzy membership function of the resisting ocean current 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 ocean current greatly.