Research on Autonomous Position and Azimuth Keeping for Aquatic Robot in Shallow Ocean

2016 Fiscal Year Final Research Report

• Project/Area Number: 15K20850
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Intelligent mechanics/Mechanical systems; Intelligent robotics
• Research Institution: Iwate University
• Principal Investigator: Kim Chyon Hae 岩手大学, 理工学部, 准教授 (30424815)
• Research Collaborator: SASAKI Yoshihisa ; TOMISAAW Takeya ; NAKAJIMA Hisayoshi ; FUNATO Shuichi ; OYAMA Hirokuni ; AKASHI Takuya ; MIYOSHI Tasuku ; OGASAWARA Toshiki ; MATSUBAYASHI Yuriko
• Project Period (FY): 2015-04-01 – 2017-03-31
• Keywords: 知能ロボット / 定点制御 / 船体制御 / 学習アルゴリズム / 動力学 / ブラックボックスモデル / 逐次学習 / 外乱

Outline of Final Research Achievements

In this research, we developed two aquatic robots and an image processing system based on optical flow in order to estimate the position of the aquatic robots. We also developed an acceleration predictor of the robots that is based on dynamics learning tree (DLT) and FAD learning. We improved the effectiveness of DLT against noise. As a result of the control experiments using these robots, we could confirm the three facts, the robots are able to come back around a goal position when there is no wave, the robots are able to cancel the affection from wave, and the robots are able to go back around goal position and azimuth even when there is wave. The learning and control methods that are developed by this research were also effective for the control of humanoid robots and vehicles.

Free Research Field

ロボティクス