Visual-Aided Shared Control of Semi-Autonomous Underwater Vehicle for Efficient Underwater Grasping

Human intelligence has the advantage for making high-level decisions in remote control of underwater vehicles, while autonomous is superior accurate and fast close-range pose adjustment. Combining advantages both control, this paper proposes a visual-aided shared-control method semi-autonomous vehicle (sAUV) to conduct flexible, efficient stable grasping. The proposed utilizes an arbitration mechanism assign authority weights human command automatic controller according attraction field (AF) generated by target objects. AF intensity adjusted understanding intention, remote-operation fused with visual servo controller. shared designed based on kinematic dynamic models, model parameter uncertainties are also addressed. Efficient performance validated simulation experiment. Faster positioning front object achieved using method. Compared pure operation mode, mode significantly reduces average time consumption grasping tasks skilled unskilled operators.