Research on the recovery system of the fixed wing swarm based on the robotic vision in the marine environment

The use of the robotic arm to achieve the recovery of the unmanned aerial vehicles(UAV) has a broad applications in the marine environment; however, due to the complexity of the marine environment(such as the cloud and snow weather, and the high light intensity), in the process of the recovery of the UAVs, the relative position relationship between the robotic arm and the UAV can not be accurately reflected based on the existing methods of the machine vision. In this work, the visual recognition algorithm based on the aruco code of the binocular camera is proposed to solve the above problem. Firstly the median filtering process is added to eliminate the salt and pepper noise in the process of the visual recognition of the two-dimensional code. Then, a new binary conversion method is carried out to obtain the accurate relative position between the robotic arm and the UAV. Finally, based on the information of the relative position, the robotic arm carries out the path planning and the control to realize recovery. The experiments indicate that in cloud and snow weather, the recovery system based on the robot vision can recovery the UAV effectively.