New Development In Robot Vision

The field of robotic vision has advanced dramatically recently with the development of new range sensors. Tremendous progress has been made resulting in significant impact on areas such as robotic navigation, scene/environment understanding, and visual learning. This edited book provides a solid and diversified reference source for some of the most recent important advancements in the field of robotic vision. The book starts with articles that describe new techniques to understand scenes from 2D/3D data such as estimation of planar structures, recognition of multiple objects in the scene using different kinds of features as well as their spatial and semantic relationships, generation of 3D object models, approach to recognize partially occluded objects, etc. Novel techniques are introduced to improve 3D perception accuracy with other sensors such as a gyroscope, positioning accuracy with a visual servoing based alignment strategy for microassembly, and increasing object recognition reliability using related manipulation motion models. For autonomous robot navigation, different vision-based localization and tracking strategies and algorithms are discussed. New approaches using probabilistic analysis for robot navigation, online learning of vision-based robot control, and 3D motion estimation via intensity differences from a monocular camera are described. This collection will be beneficial to graduate students, researchers, and professionals working in the area of robotic vision.

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.

"Presents a solid framework for understanding existing work and planning future research."--Cover.

Industrial robots carry out simple tasks in customized environments for which it is typical that nearly all e?ector movements can be planned during an - line phase. A continual control based on sensory feedback is at most necessary at e?ector positions near target locations utilizing torque or haptic sensors. It is desirable to develop new-generation robots showing higher degrees of autonomy for solving high-level deliberate tasks in natural and dynamic en- ronments. Obviously, camera-equipped robot systems, which take and process images and make use of the visual data, can solve more sophisticated robotic tasks. The development of a (semi-) autonomous camera-equipped robot must be grounded on an infrastructure, based on which the system can acquire and/or adapt task-relevant competences autonomously. This infrastructure consists of technical equipment to support the presentation of real world training samples, various learning mechanisms for automatically acquiring function approximations, and testing methods for evaluating the quality of the learned functions. Accordingly, to develop autonomous camera-equipped robot systems one must ?rst demonstrate relevant objects, critical situations, and purposive situation-action pairs in an experimental phase prior to the application phase. Secondly, the learning mechanisms are responsible for - quiring image operators and mechanisms of visual feedback control based on supervised experiences in the task-relevant, real environment. This paradigm of learning-based development leads to the concepts of compatibilities and manifolds. Compatibilities are general constraints on the process of image formation which hold more or less under task-relevant or accidental variations of the imaging conditions.

Industrial robots carry out simple tasks in customized environments for which it is typical that nearly all e?ector movements can be planned during an - line phase. A continual control based on sensory feedback is at most necessary at e?ector positions near target locations utilizing torque or haptic sensors. It is desirable to develop new-generation robots showing higher degrees of autonomy for solving high-level deliberate tasks in natural and dynamic en- ronments. Obviously, camera-equipped robot systems, which take and process images and make use of the visual data, can solve more sophisticated robotic tasks. The development of a (semi-) autonomous camera-equipped robot must be grounded on an infrastructure, based on which the system can acquire and/or adapt task-relevant competences autonomously. This infrastructure consists of technical equipment to support the presentation of real world training samples, various learning mechanisms for automatically acquiring function approximations, and testing methods for evaluating the quality of the learned functions. Accordingly, to develop autonomous camera-equipped robot systems one must ?rst demonstrate relevant objects, critical situations, and purposive situation-action pairs in an experimental phase prior to the application phase. Secondly, the learning mechanisms are responsible for - quiring image operators and mechanisms of visual feedback control based on supervised experiences in the task-relevant, real environment. This paradigm of learning-based development leads to the concepts of compatibilities and manifolds. Compatibilities are general constraints on the process of image formation which hold more or less under task-relevant or accidental variations of the imaging conditions.

I. ALEKSANDER Department of Electrical Engineering and Electronics BruneI University, England The three key words that appear in the title of this book need some clarification. First, how far does the word robot reach in the context of indus trial automation? There is an argument maintaining that this range is not fixed, but increases with advancing technology. The most limited definition of the robot is also the earliest. The history is worth following because it provides a convincing backdrop to the central point of this book: vision is likely to epitomize the technolo gical advance, having the greatest effect in enlarging the definition and range of activity of robots. In the mid 1950s it was foreseen that a purely mechanical arm-like device could be used to move objects between two fixed locations. This was seen to be cost-effective only if the task was to remain fixed for some time. The need to change tasks and therefore the level of programmability of the robot was a key issue in the broadening of robot activities. Robots installed in industry in the early 1960s derived their programmability from a device called apinboard. Ver tical wires were energized sequentially in time, while horizontal wires, when energized, would trigger off elementary actions in the manipulator arm. The task of reprogramming was a huge one, as pins had to be reinserted in the board, connecting steps in time with robot actions.

In 1986, B.K.P. Horn published a book entitled Robot Vision, which actually discussed a wider ?eld of subjects, basically addressing the ?eld of computer vision, but introducing “robot vision” as a technical term. Since then, the - teraction between computer vision and research on mobile systems (often called “robots”, e.g., in an industrial context, but also including vehicles, such as cars, wheelchairs, tower cranes, and so forth) established a diverse area of research, today known as robot vision. Robot vision (or, more general, robotics) is a fast-growing discipline, already taught as a dedicated teaching program at university level. The term “robot vision” addresses any autonomous behavior of a technical system supported by visual sensoric information. While robot vision focusses on the vision process, visual robotics is more directed toward control and automatization. In practice, however, both ?elds strongly interact. Robot Vision 2008 was the second international workshop, counting a 2001 workshop with identical name as the ?rst in this series. Both workshops were organized in close cooperation between researchers from New Zealand and Germany, and took place at The University of Auckland, New Zealand. Participants of the 2008 workshop came from Europe, USA, South America, the Middle East, the Far East, Australia, and of course from New Zealand.

This book constitutes the refereed proceedings of the International Workshop on Robot Vision, RobVis 2001, held in Auckland, New Zealand in February 2001.The 17 revised full papers presented together with 17 posters were carefully reviewed and selected from 52 submissions. The papers and posters are organized in topical sections on active perception, computer vision, robotics and video, computational stereo, robotic vision, and image acquisition.