Control Method of Underwater Manipulator Based on Fusion of Somatosensory and Visual Information

Aiming at the problems of great control difficulty, low manual control accuracy and low operation efficiency of underwater manipulator, a control method of underwater manipulator based on somatosensory and visual information collaborative control is proposed. Firstly, the angle data of human arm motion is collected by somatosensory equipment and discretized into angular velocity data. Secondly, the binocular camera is used to collect the position information of the target. After filtering, it is converted into the target angle output by each joint according to the inverse kinematics of the manipulator. Finally, the somatosensory and visual control data in each accumulated control information are weighted and fused according to the adaptive weight to achieve accurate convergence of each joint angle. The experimental results show that the control method proposed in this paper has good robustness and efficiency. Compared with manual control, the time required to achieve the target pose is reduced by 16.02 % and 40.75 % respectively in the two groups of experiments. Compared with the fixed weight fusion control, this method has better self-regulation performance, and improves the human-computer interaction while significantly improving the control efficiency.