Visual Perception and Control of Underwater Robots covers theories and applications from aquatic visual perception and underwater robotics. Within the framework of visual perception for underwater operations, image restoration, binocular measurement, and object detection are addressed. More specifically, the book includes adversarial critic learning for visual restoration, NSGA-II-based calibration for binocular measurement, prior knowledge refinement for object detection, analysis of temporal detection performance, as well as the effect of the aquatic data domain on object detection. With the aid of visual perception technologies, two up-to-date underwater robot systems are demonstrated. The first system focuses on underwater robotic operation for the task of object collection in the sea. The second is an untethered biomimetic robotic fish with a camera stabilizer, its control methods based on visual tracking. The authors provide a self-contained and comprehensive guide to understand underwater visual perception and control. Bridging the gap between theory and practice in underwater vision, the book features implementable algorithms, numerical examples, and tests, where codes are publicly available. Additionally, the mainstream technologies covered in the book include deep learning, adversarial learning, evolutionary computation, robust control, and underwater bionics. Researchers, senior undergraduate and graduate students, and engineers dealing with underwater visual perception and control will benefit from this work.

This book reports on the latest advances in the study of motion control in biomimetic swimming robots with high speed and high manoeuvrability. It presents state-of-the-art studies on various swimming robots including robotic fish, dolphins and jellyfish in a unified framework, and discusses the potential benefits of applying biomimetic underwater propulsion to autonomous underwater vehicle design, such as: speed, energy economy, enhanced manoeuvrability, and reduced detectability. Given its scope, the book will be of interest to researchers, engineers and graduate students in robotics and ocean engineering who wish to learn about the core principles, methods, algorithms, and applications of biomimetic underwater robots.

Underwater robots play a significant role in ocean exploration. This book provides full coverage of the theoretical and practical aspects of bionic gliding underwater robots, including system design, modeling control, and motion planning. To overcome the inherent shortcomings of traditional underwater robots that can simultaneously lack maneuverability and endurance, a new type of robot, the bionic gliding underwater robot, has attracted much attention from scientists and engineers. On the one hand, by imitating the appearance and swimming mechanisms of natural creatures, bionic gliding underwater robots achieve high maneuverability, swimming efficiency, and strong concealment. On the other hand, borrowing from the buoyancy adjustment systems of underwater gliders, bionic gliding underwater robots can obtain strong endurance, which is significant in practical applications. Taking gliding robotic dolphin and fish as examples, the designed prototypes and proposed methods are discussed, offering valuable insights into the development of next-generation underwater robots that are well suited for various oceanic applications. This book will be of great interest to students and professionals alike in the field of robotics or intelligent control. It will also be a great reference for engineers or technicians who deal with the development of underwater robots.

This chapter has reviewed some of the issues involved in creating a multiple robotic fish cooperation platform inspired by the astonishing cooperative power exhibited by fish school. Grounded on an optimized kinematic and dynamic model of robotic fish, a group of radio-controlled, multi-link fish-like robots as well as their motion control were developed. To enable a closed control loop, a vision-based multi-object tracking subsystem for multiple robotic fish was built, where an improved parallel visual tracking method is formulated within a framework synthesizing features of fish features and surrounding disturbance. A hierarchical architecture for the artificial multi-fish system was further proposed to generate coordinated behaviours and actions. Experimental results on three typical cooperation tasks demonstrated the effectiveness of the proposed scheme. The ongoing and future work will focus on developing a 3-D dynamic model for freeswimming, multi-link robots and on investigating experimentally the corresponding control laws, which makes preparations for cooperative control of multiple robotic fish in 3-D aquatic environments. In addition, some learning algorithms will be incorporated into the cooperative framework to enhance the cooperation efficiency.

Localization and mapping play a critical role in the autonomous task execution of mobile robots. This book covers the theoretical and technological aspects of robot localization and mapping, including visual localization and mapping, visual relocalization, LiDAR localization and mapping, and place recognition. It provides the theoretical foundations of robot localization and mapping. It employs both traditional methods, such as geometry-based visual localization, and state-of-the-art deep learning techniques that improve robot perception. The authors also address LiDAR-based localization, exploring techniques to improve both efficiency and accuracy when processing dense point clouds. Key topics include visual localization using deep features, integration of visual solutions under ROS-based software architecture, and distribution-based LiDAR localization, etc. This book will be of great interest to students and professionals in the field of robotics or artificial intelligence. It will also be an excellent reference for engineers or technicians involved in the development of robot localization.

This project is a demonstration of heritage landscape preservation done through a new design for Franklin Park in Boston, Massachusetts. Design from a preservation perspective requires sensitivity to the interacting forces between site history, existing conditions, and future needs, especially when engaging a historical landscape that was designed by a renowned figure like Olmsted. The goals of this project are to rehabilitate the Franklin Park site, securing its integrity and historical value, while allowing changes and future growth to take place.

The book reveals many different aspects of motion control and a wide multiplicity of approaches to the problem as well. Despite the number of examples, however, this volume is not meant to be exhaustive: it intends to offer some original insights for all researchers who will hopefully make their experience available for a forthcoming publication on the subject.

Essence of arts.