Visual Perception and Control of Underwater Robots

The book "Visual Perception and Control of Underwater Robots" covers underwater visual perception and control theories and applications, including image restoration, binocular measurement, and object detection. Two underwater robot systems are demonstrated, focusing on object collection and biomimetic robotic fish. It provides a comprehensive guide with implementable algorithms, numerical examples, and tests, covering deep learning, adversarial learning, evolutionary computation, robust control, and underwater bionics. Researchers, senior undergraduate and graduate students, and engineers will benefit from this work.

Format: Paperback / softback
Length: 236 pages
Publication date: 26 September 2022
Publisher: Taylor & Francis Ltd

Visual Perception and Control of Underwater Robots delves into the realm of aquatic visual perception and underwater robotics, encompassing a wide range of theories and applications. Within the framework of underwater operations, the book addresses key aspects such as image restoration, binocular measurement, and object detection. It explores advanced techniques like adversarial critic learning for visual restoration, NSGA-II-based calibration for binocular measurement, prior knowledge refinement for object detection, analysis of temporal detection performance, and the influence of the aquatic data domain on object detection.

To illustrate the practical applications of underwater visual perception and control, two cutting-edge underwater robot systems are showcased. The first system revolves around underwater robotic operations for the task of object collection in the sea. The second system involves an untethered biomimetic robotic fish equipped with a camera stabilizer, its control methods based on visual tracking.

The authors offer a comprehensive and self-contained guide to unravel the complexities of underwater visual perception and control. By bridging the gap between theory and practice in underwater vision, the book provides implementable algorithms, numerical examples, and tests, with the codes publicly available for further exploration. Additionally, the book covers mainstream technologies such as deep learning, adversarial learning, evolutionary computation, robust control, and underwater bionics, making it invaluable for researchers, senior undergraduate and graduate students, and engineers engaged in underwater visual perception and control.

Weight: 376g
Dimension: 152 x 229 x 18 (mm)
ISBN-13: 9780367700300