Artificial Vision For Mobile Robots

To give mobile robots real autonomy, and to permit them to act efficiently in a diverse, cluttered, and changing environment, they must be equipped with powerful tools for perception and reasoning. Artificial Vision for Mobile Robots presents new theoretical and practical tools useful for providing mobile robots with artificial vision in three dimensions, including passive binocular and trinocular stereo vision, local and global 3D map reconstructions, fusion of local 3D maps into a global 3D map, 3D navigation, control of uncertainty, and strategies of perception. Numerous examples from research carried out at INRIA with the Esprit Depth and Motion Analysis project are presented in a clear and concise manner. Nicolas Ayache is Research Director at INRIA, Le Chesnay, France. Contents. General Introduction. Stereo Vision. Introduction. Calibration. Image Representation. Binocular Stereo Vision Constraints. Binocular Stereo Vision Algorithms. Experiments in Binocular Stereo Vision. Trinocular Stereo Vision, Outlook. Multisensory Perception. Introduction. A Unified Formalism. Geometric Representation. Construction of Visual Maps. Combining Visual Maps. Results: Matching and Motion. Results: Matching and Fusion. Outlook.

The book is intended for advanced students in physics, mathematics, computer science, electrical engineering, robotics, engine engineering and for specialists in computer vision and robotics on the techniques for the development of vision-based robot projects. It focusses on autonomous and mobile service robots for indoor work, and teaches the techniques for the development of vision-based robot projects. A basic knowledge of informatics is assumed, but the basic introduction helps to adjust the knowledge of the reader accordingly. A practical treatment of the material enables a comprehensive understanding of how to handle specific problems, such as inhomogeneous illumination or occlusion. With this book, the reader should be able to develop object-oriented programs and show mathematical basic understanding. Such topics as image processing, navigation, camera types and camera calibration structure the described steps of developing further applications of vision-based robot projects.

Vision-based control of wheeled mobile robots is an interesting field of research from a scientific and even social point of view due to its potential applicability. This book presents a formal treatment of some aspects of control theory applied to the problem of vision-based pose regulation of wheeled mobile robots. In this problem, the robot has to reach a desired position and orientation, which are specified by a target image. It is faced in such a way that vision and control are unified to achieve stability of the closed loop, a large region of convergence, without local minima and good robustness against parametric uncertainty. Three different control schemes that rely on monocular vision as unique sensor are presented and evaluated experimentally. A common benefit of these approaches is that they are valid for imaging systems obeying approximately a central projection model, e.g., conventional cameras, catadioptric systems and some fisheye cameras. Thus, the presented control schemes are generic approaches. A minimum set of visual measurements, integrated in adequate task functions, are taken from a geometric constraint imposed between corresponding image features. Particularly, the epipolar geometry and the trifocal tensor are exploited since they can be used for generic scenes. A detailed experimental evaluation is presented for each control scheme.

The mobile robot systems described in this book were selected from among the best available implementations by leading universities and research laboratories. These are robots that have left the lab and been tested in natural and unknown environments. They perform many different tasks, from giving tours to collecting trash. Many have distinguished themselves (usually with first- or second-place finishes) at various indoor and outdoor mobile robot competitions. Each case study is self-contained and includes detailed descriptions of important algorithms, including pseudo-code. Thus this volume serves as a recipe book for the design of successful mobile robot applications. Common themes include navigation and mapping, computer vision, and architecture. Contributors Ronald Arkin, Tucker Balch, Michael Brady, Don Brutzman, Arno Bucken, R. James Firby, Erann Gat, Tony Healy, Ian Horswill, Housheng Hu, Sven Koenig, Kurt Konolige David Kortenkamp, Dave Marco, Bob McGhee, Robin Murphy, Karen Myers, Illah Nourbakhsh, Peter Prokopowicz, Bill Schiller, Reid Simmons, Michael Swain, Sebastian Thrun

Robotic systems consist of object or scene recognition, vision-based motion control, vision-based mapping, and dense range sensing, and are used for identification and navigation. As these computer vision and robotic connections continue to develop, the benefits of vision technology including savings, improved quality, reliability, safety, and productivity are revealed. Robotic Vision: Technologies for Machine Learning and Vision Applications is a comprehensive collection which highlights a solid framework for understanding existing work and planning future research. This book includes current research on the fields of robotics, machine vision, image processing and pattern recognition that is important to applying machine vision methods in the real world.

Mobile robots are the focus of a great deal of current research in robotics. Mobile robotics is a young, multidisciplinary field involving knowledge from many areas, including electrical, electronic and mechanical engineering, computer, cognitive and social sciences. Being engaged in the design of automated systems, it lies at the intersection of artificial intelligence, computational vision, and robotics. Thanks to the numerous researchers sharing their goals, visions and results within the community, mobile robotics is becoming a very rich and stimulating area. The book Recent Advances in Mobile Robotics addresses the topic by integrating contributions from many researchers around the globe. It emphasizes the computational methods of programming mobile robots, rather than the methods of constructing the hardware. Its content reflects different complementary aspects of theory and practice, which have recently taken place. We believe that it will serve as a valuable handbook to those who work in research and development of mobile robots.

Many robotics researchers consider high-level vision algorithms (computational) too expensive for use in robot guidance. This book introduces the reader to an alternative approach to perception for autonomous, mobile robots. It explores how to apply methods of high-level computer vision and fuzzy logic to the guidance and control of the mobile robot. The book introduces a knowledge-based approach to vision modeling for robot guidance, where advantage is taken of constraints of the robot's physical structure, the tasks it performs, and the environments it works in. This facilitates high-level computer vision algorithms such as object recognition at a speed that is sufficient for real-time navigation. The texts presents algorithms that exploit these constraints at all levels of vision, from image processing to model construction and matching, as well as shape recovery. These algorithms are demonstrated in the navigation of a wheeled mobile robot.

Create end-to-end systems that can power robots with artificial vision and deep learning techniques Key FeaturesStudy ROS, the main development framework for robotics, in detailLearn all about convolutional neural networks, recurrent neural networks, and roboticsCreate a chatbot to interact with the robotBook Description Artificial Vision and Language Processing for Robotics begins by discussing the theory behind robots. You'll compare different methods used to work with robots and explore computer vision, its algorithms, and limits. You'll then learn how to control the robot with natural language processing commands. You'll study Word2Vec and GloVe embedding techniques, non-numeric data, recurrent neural network (RNNs), and their advanced models. You'll create a simple Word2Vec model with Keras, as well as build a convolutional neural network (CNN) and improve it with data augmentation and transfer learning. You'll study the ROS and build a conversational agent to manage your robot. You'll also integrate your agent with the ROS and convert an image to text and text to speech. You'll learn to build an object recognition system using a video. By the end of this book, you'll have the skills you need to build a functional application that can integrate with a ROS to extract useful information about your environment. What you will learnExplore the ROS and build a basic robotic systemUnderstand the architecture of neural networksIdentify conversation intents with NLP techniquesLearn and use the embedding with Word2Vec and GloVeBuild a basic CNN and improve it using generative modelsUse deep learning to implement artificial intelligence(AI)and object recognitionDevelop a simple object recognition system using CNNsIntegrate AI with ROS to enable your robot to recognize objectsWho this book is for Artificial Vision and Language Processing for Robotics is for robotics engineers who want to learn how to integrate computer vision and deep learning techniques to create complete robotic systems. It will prove beneficial to you if you have working knowledge of Python and a background in deep learning. Knowledge of the ROS is a plus.