Underwater terminal docking system and method based on light vision guidance

Abstract

The invention discloses an underwater terminal autonomous docking system and method based on light vision guidance. The system comprises an underwater docking station and an autonomous underwater robot used for docking. The underwater docking station adopts a frame type configuration, and six identification light sources are mounted at specific positions of the underwater docking station to construct a three-dimensional guide lamp array; the underwater robot is provided with an underwater camera and an image processing unit in addition to the capability of autonomous navigation, and the underwater camera and the image processing unit are used for collecting and processing underwater images. The underwater terminal autonomous docking method comprises an underwater image processing method and a staged docking control method. According to the image processing method, the relative pose amount of the robot and the docking station is calculated according to image information collected by the camera, and the position tracking deviation of the robot is calculated according to the relative pose amount. Based on different results obtained by shooting a guide lamp array by a camera at different distances, a long-distance and short-distance staged docking control method is designed, and docking control of the robot is realized by adopting different docking control strategies.

Description

technical field [0001] The present invention relates to the field of marine engineering and technology, to the field of autonomous docking and recovery of autonomous underwater robots, and more specifically, to an underwater terminal docking system and method based on optical vision guidance. Background technique [0002] Autonomous underwater vehicle (AUV) has the characteristics of high degree of automation, good flexibility, and long working time, but it also faces many practical problems during use. These highly automated equipment usually carry limited energy, and there is a need for energy supplementation after the mission is completed or even during the mission. In addition, data interaction and equipment maintenance are required in a timely manner. Recycle. Among them, underwater autonomous docking and recovery technology is a hotspot of current research. [0003] The autonomous docking and recovery of underwater robots is generally divided into two stages: 1) AUV ...

AI Technical Summary

Problems solved by technology

Pure visual guidance has high requirements on water quality, relatively short guiding distance, and poor environmental adaptability; at the same time, since the docking station does not have an active guiding light source, it is difficult for underwater robots to capture docking station targets

Since the single-eye and single-light guidance cannot obtain distance information, it can only be guided by horizontal deflection angle and vertical deflection angle. It cannot guarantee that the orientation of the robot when it docks is consistent with the orientation of the opening of the docking station. The risk of collision is relatively high, and the success rate of docking is relatively low.

In addition, in the existing single-eye multi-light guidance scheme, the guide light sources are basically arranged on the same plane as the opening of the docking station. Due to the limited field of view of the camera, when the distance is very close (within about 1-2 meters), the camera The guiding light source will be lost, making it impossible to correct the deviation in the final stage, which is not conducive to docking

However, the binocular system itself is relatively complex, and the poor underwater imaging quality leads to low accuracy in solving the disparity map, which also has certain application limitations.

Images