期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 8, 期 4, 页码 2277-2284出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2023.3250004
关键词
Robot kinematics; Location awareness; Cameras; Task analysis; Robot vision systems; Turning; Sports; Biologically-inspired robots; robotic manta; target following control; binocular underwater localization; sliding mode control
类别
This letter proposes a vision-based underwater target following scheme for robotic manta by constructing an agile robotic manta equipped with a binocular camera system and conceiving a color-based underwater target detection and localization method. A robust target following controller is presented to solve the coupling between distance and azimuth control of the robot by combining the nonsingular terminal sliding mode controller and fuzzy inference system.
Manta-inspired robots have been increasingly applied in vision-based underwater tasks. However, owing to the refraction effect and motion coupling problem, their accurate target following control is still poorly understood. This letter proposes a vision-based underwater target following scheme for robotic manta. First, an agile robotic manta equipped with a binocular camera system is constructed. The motion modes are further detailed based on the propulsion analysis to the flexible pectoral fins. Second, a color-based underwater target detection and localization method is conceived. Specifically, the binocular refraction correction is employed to improve the localization accuracy. Third, combing the nonsingular terminal sliding mode controller and fuzzy inference system, a robust target following controller is presented to solve the coupling between distance and azimuth control of the robot. Finally, various aquatic experiments are conducted, verifying the effectiveness and robustness of the proposed underwater target following scheme. The obtained results provide valuable insights into the intelligent control of agile bioinspired robots performing vision-based tasks in dynamic underwater environments.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据