Underwater Target Following with a Vision-based Autonomous Robotic Fish

This paper is concerned with vision-based target following control of an autonomous, ostraciiform swimming robotic fish. Based on the successful development and effective swimming locomotion control of the robotic fish prototype, we further investigate the utility of the onboard digital camera in target following task, the output of which can be processed with the embedded processor. To treat the degradation of underwater images, a modified continuously adaptive mean shift (Camshift) algorithm is employed to keep visual lock on the moving target. A fuzzy logic controller is designed for motion regulation of a hybrid swimming pattern, which employs synchronized pectoral fins for thrust generation and tail fin for steering. A simple target following task is designed via an autonomous robotic fish swimming after a manually controlled robotic fish with fixed distance. Experimental results verify the effectiveness of the proposed methods.