This book tackles all the stages and mechanisms involved in the learning of manipulation tasks by bimanual robots in unstructured settings, as it can be the task of folding clothes. The first part describes how to build an integrated system, capable of properly handling the kinematics and dynamics of the robot along the learning process. It proposes practical enhancements to closed-loop inverse kinematics for redundant robots, a procedure to position the two arms to maximize workspace manipulability, and a dynamic model together with a disturbance observer to achieve compliant control and safe robot behavior. In the second part, methods for robot motion learning based on movement primitives and direct policy search algorithms are presented. To improve sampling efficiency and accelerate learning without deteriorating solution quality, techniques for dimensionality reduction, for exploiting low-performing samples, and for contextualization and adaptability to changing situations are proposed. In sum, the reader will find in this comprehensive exposition the relevant knowledge in different areas required to build a complete framework for model-free, compliant, coordinated robot motion learning.

This book tackles all the stages and mechanisms involved in the learning of manipulation tasks by bimanual robots in unstructured settings, as it can be the task of folding clothes. The first part describes how to build an integrated system, capable of properly handling the kinematics and dynamics of the robot along the learning process. It proposes practical enhancements to closed-loop inverse kinematics for redundant robots, a procedure to position the two arms to maximize workspace manipulability, and a dynamic model together with a disturbance observer to achieve compliant control and safe robot behavior. In the second part, methods for robot motion learning based on movement primitives and direct policy search algorithms are presented. To improve sampling efficiency and accelerate learning without deteriorating solution quality, techniques for dimensionality reduction, for exploiting low-performing samples, and for contextualization and adaptability to changing situations are proposed. In sum, the reader will find in this comprehensive exposition the relevant knowledge in different areas required to build a complete framework for model-free, compliant, coordinated robot motion learning.

This book is the fruit of a very long and elaborate process. It was conceived as a comprehensive solution to several deficiencies encountered while trying to teach the essentials of Computer Vision in different contexts: to technicians from industry looking for technological solutions to some of their problems, to students in search of a good subject for a PhD thesis, and to researchers in other fields who believe that Computer Vision techniques may help them to analyse their results. The book was carefully planned with all these people in mind. Thus, it covers the fundamentals of both 2D and 3D Computer Vision and their most widespread industrial applications, such as automated inspection, robot guidance and workpiece acquisition. The level of explanation is that of an expanded introductory text, in the sense that, besides the basic material, some special advanced topics are included in each chapter, together with an extensive bibliography for experts to follow up. Well-known researchers on each of the topics were appointed to write a chapter following several guidelines to ensure a consistent presentation throughout. I would like to thank the authors for their patience, because some of them had to go through several revisions of their chapters in order to avoid repetition and to improve the homogeneity and coherence of the book. I hope they will find that the final result has been worth their efforts.

While the ability of animals to learn rhythms is an unquestionable fact, the underlying neurophysiological mechanisms are still no more than conjectures. This monograph explores the requirements of such mechanisms, reviews those previously proposed and postulates a new one based on a direct electric coding of stimulation frequencies. Experi mental support for the option taken is provided both at the single neuron and neural network levels. More specifically, the material presented divides naturally into four parts: a description of the experimental and theoretical framework where this work becomes meaningful (Chapter 2), a detailed specifica tion of the pacemaker neuron model proposed together with its valida tion through simulation (Chapter 3), an analytic study of the behavior of this model when submitted to rhythmic stimulation (Chapter 4) and a description of the neural network model proposed for learning, together with an analysis of the simulation results obtained when varying seve ral factors related to the connectivity, the intraneuronal parameters, the initial state and the stimulation conditions (Chapter 5). This work was initiated at the Computer and Information Science Depart ment of the University of Massachusetts, Amherst, and completed at the Institut de c Lber n e t Lca of the Universitat Politecnica de Catalunya, Barcelona. Computers at the latter place have adopted Catalan as their mother tongue and thus some computer-made figures in this monograph, specially those in Chapter 5, appear labeled in that tongue."