摘要：Aiming at developing underwater battery recharging system, we have been researching on automatic docking of an underwater robot using dual-eyes-based visual servoing and 3D marker without emission of light (passive 3D marker). In our previous researches, we conducted docking experiments in seaarea, having verified the effectiveness in the day time in an environment with less turbid water condition. Given the situation that the docking aims for battery recharging in deep sea bottom, pitch-dark and turbid environment should be considered as inevitable condition. Since lighting passive 3Dmarker from vehicle in turbid water environment results in the images taken by video cameras set on the vehicle being looked wholly white, some new idea seems to be required. Our proposal to overcome this difficulty is to introduce a lighting 3D marker (active 3D marker) that has LEDs inside. Inthis paper, recognition performances using active and passive 3D marker are compared, having confirmed that the new active marker with no-lighting from a vehicle could be recognizable in dark and turbid environment than the passive marker lighted from the vehicle. This has contributed to the actualsea docking in pitch-dark real sea environment.
