主催: 一般社団法人 日本機械学会
会議名: ロボティクス・メカトロニクス 講演会2018
開催日: 2018/06/02 - 2018/06/05
Nowadays, autonomous underwater vehicles (AUVs) have been studied and developed for undersea exploration in order to discover an abundant seabed resources. It is necessary for the robot to work long time in deep sea in order to efficiently perform such a novel work. We have developed a dual-eye based docking approach for underwater battery recharging to enable the AUV to operate for extended period without returning sea surface for recharging. The 3D pose estimation for real time docking performance was improved by using active/lighting 3D marker against turbidity under dark environment. In this paper, we analyzed the effectiveness of the light intensity of the active 3D marker by changing the current of each LED that was installed in 3D marker. The experimental results have confirmed that the recognition accuracy of the proposed system was improved by using optimized lighting intensity.