Embedded Vision-Guided 3-D Tracking Control for Robotic Fish

Abstract

Visual tracking of free-swimming robotic fish remains a great challenge by considering imaging qualities in aquatic environments. In this paper, we propose a visual identification and positioning method to obtain accurate position for 3-D tracking control comprising depth control and directional control. Specifically, a depth control method based on fuzzy sliding-mode control is put forward to make the robotic fish swim to the preferred target depth and remain at that depth. A directional control method with multiple stages is proposed, and a series of control strategies is developed to integrate agile locomotion and control accuracy. Experiments on depth control and 3-D tracking control are finally conducted in an indoor pool. The latest results obtained indicate that the proposed algorithms are effective and feasible, which lays a solid foundation for complex underwater task execution.