海流下におけるUUVのための生体模倣ニューラルネットワークに基づく最適経路計画
Bio-inspired Neural Network-based Optimal Path Planning for UUVs under the Effect of Ocean Currents
海流の影響を打ち消しながら衝突を避けて最短経路を導出する、ニューラルネットワークベースのUUV向け経路計画アルゴリズムを提案し、海流を考慮しない手法との比較で有効性を示した。
著者: Danjie Zhu, Simon X. Yang
分類: cs.RO, cs.SY, eess.SY
原文アブストラクト
To eliminate the effect of ocean currents when addressing the optimal path in the underwater environment, an intelligent algorithm designed for the unmanned underwater vehicle (UUV) is proposed in this paper. The algorithm consists of two parts: a neural network-based algorithm that deducts the shortest path and avoids all possible collisions; and an adjusting component that balances off the deviation brought by the effect of ocean currents. The optimization results of the proposed algorithm are presented in detail, and compared with the path planning algorithm that does not consider the effect of currents. Results of the comparison prove the effectiveness of the path planning method when encountering currents of different directions and velocities.
