B301 モジュラー型自己組織化マップを用いた水中ロボットのシステム同定(OS10 海洋におけるシステムと制御1)

概要

論文の詳細を見る
Underwater robots and underwater machine are counted on helping the salvage procedure, escaping prevention of pollution, lifesaving at sea, scientific exploration in the ocean and so on. In the point of the Deep-sea exploration, underwater robots can contribute to prosperity and achievement of discovering new animate beings, mendelian factor and ancient earth environment. In the underwater robot, therefore, Autonomous Underwater Vehicles (AUVs) have been developed actively during recent years. However, AUVs have various problems which should be solved such as motion control, acquisition of sensors' information, behavioral decision self-localization and so on. Regarding to consider about these problems, robot should be learning on self-organizing about relationship to own status and environment and behaviors. Therefore, a new method, which keeps the information of initial knowledge or previous environment and adapts to new environment, should be developed for improving the efficiency of the learning and reducing the learning cost with the use of the former environmental information that the robot had already learned. In this paper, a new self-organizing controllers system for AUVs using modular network SOM proposed by Tokunaga et al., is described. The proposed control system is developed using Reccurent Neural Network (RNN) type mnSOM. And, we report that the modify points of this controller system.
一般社団法人日本機械学会の論文
2011-06-28

B301 モジュラー型自己組織化マップを用いた水中ロボットのシステム同定(OS10 海洋におけるシステムと制御1)

スポンサーリンク

概要

著者

関連論文

スポンサーリンク