This book introduces the challenges of robotic tactile perception and task understanding, and describes an advanced approach based on machine learning and sparse coding techniques. Further, a set of structured sparse coding models is developed to address the issues of dynamic tactile sensing. The book then proves that the proposed framework is effective in solving the problems of multi-finger tactile object recognition, multi-label tactile adjective recognition and multi-category material analysis, which are all challenging practical problems in the fields of robotics and automation. The proposed sparse coding model can be used to tackle the challenging visual-tactile fusion recognition problem, and the book develops a series of efficient optimization algorithms to implement the model. It is suitable as a reference book for graduate students with a basic knowledge of machine learning as well as professional researchers interested in robotic tactile perception and understanding, and machine learning.
Future robots are expected to work closely and interact safely with real-world objects and humans alike. Sense of touch is important in this context, as it helps estimate properties such as shape, texture, hardness, material type and many more; provides action related information, such as slip detection; and helps carrying out actions such as rolling an object between fingers without dropping it. This book presents an in-depth description of the solutions available for gathering tactile data, obtaining aforementioned tactile information from the data and effectively using the same in various robotic tasks. The efforts during last four decades or so have yielded a wide spectrum of tactile sensing technologies and engineered solutions for both intrinsic and extrinsic touch sensors. Nowadays, new materials and structures are being explored for obtaining robotic skin with physical features like bendable, conformable, and stretchable. Such features are important for covering various body parts of robots or 3D surfaces. Nonetheless, there exist many more hardware, software and application related issues that must be considered to make tactile sensing an effective component of future robotic platforms. This book presents an in-depth analysis of various system related issues and presents the trade-offs one may face while developing an effective tactile sensing system. For this purpose, human touch sensing has also been explored. The design hints coming out of the investigations into human sense of touch can be useful in improving the effectiveness of tactile sensory modality in robotics and other machines. Better integration of tactile sensors on a robot’s body is prerequisite for the effective utilization of tactile data. The concept of semiconductor devices based sensors is an interesting one, as it allows compact and fast tactile sensing systems with capabilities such as human-like spatio-temporal resolution. This book presents a comprehensive description of semiconductor devices based tactile sensing. In particular, novel Piezo Oxide Semiconductor Field Effect Transistor (POSFET) based approach for high resolution tactile sensing has been discussed in detail. Finally, the extension of semiconductors devices based sensors concept to large and flexile areas has been discussed for obtaining robotic or electronic skin. With its multidisciplinary scope, this book is suitable for graduate students and researchers coming from diverse areas such robotics (bio-robots, humanoids, rehabilitation etc.), applied materials, humans touch sensing, electronics, microsystems, and instrumentation. To better explain the concepts the text is supported by large number of figures.
Tactile Sensing, Skill Learning and Robotic Dexterous Manipulation focuses on cross-disciplinary lines of research and groundbreaking research ideas in three research lines: tactile sensing, skill learning and dexterous control. The book introduces recent work about human dexterous skill representation and learning, along with discussions of tactile sensing and its applications on unknown objects' property recognition and reconstruction. Sections also introduce the adaptive control schema and its learning by imitation and exploration. Other chapters describe the fundamental part of relevant research, paying attention to the connection among different fields and showing the state-of-the-art in related branches. The book summarizes the different approaches and discusses the pros and cons of each. Chapters not only describe the research but also include basic knowledge that can help readers understand the proposed work, making it an excellent resource for researchers and professionals who work in the robotics industry, haptics and in machine learning. - Provides a review of tactile perception and the latest advances in the use of robotic dexterous manipulation - Presents the most detailed work on synthesizing intelligent tactile perception, skill learning and adaptive control - Introduces recent work on human's dexterous skill representation and learning and the adaptive control schema and its learning by imitation and exploration - Reveals and illustrates how robots can improve dexterity by modern tactile sensing, interactive perception, learning and adaptive control approaches
The book covers different aspects: - Innovative technologies for tactile sensors development - Tactile data interpretation for control purposes - Alternative sensing technologies - Multi-sensor systems for grasping and manipulation - Sensing solutions for impaired people
This book explains the mechanisms underpinning the tactile perception of electrovibration and lays the groundwork for delivering realistic haptic feedback on touchscreens via this method. Effective utilization of electrovibration can only be accomplished by simultaneously investigating both the physical and perceptual aspects of the finger-touchscreen interaction. Towards this goal, present work blends the available knowledge on electromechanical properties of the human finger and human tactile perception with the results of new psychophysical experiments and physical measurements. By following such an approach that combines both theoretical and experimental information, the study proposes new methods and insights on generating realistic haptic effects, such as textures and edges on these displays. Besides, state-of-the-art research on the field is reviewed, and future work is discussed. The presented interdisciplinary methods and insights can interest students, broad communities of haptics, neuroscience, engineering, physics, and cognitive sciences, as well as user-interaction experts and product designers from the industry.
This volume contains 50 papers presented at the 12th International Symposium of Robotics Research, which took place October 2005 in San Francisco, CA. Coverage includes: physical human-robot interaction, humanoids, mechanisms and design, simultaneous localization and mapping, field robots, robotic vision, robot design and control, underwater robotics, learning and adaptive behavior, networked robotics, and interfaces and interaction.
Scholarpedia’s Encyclopedia of Touch provides a comprehensive collection of peer-reviewed articles written by leading researchers, detailing our current scientific understanding of tactile sensing and its neural substrates in animals including humans. The encyclopedia allows ideas and insights to be shared between researchers working on different aspects of touch and in different species, including research in synthetic touch systems. In addition, this encyclopedia raises awareness of research in tactile sensing and increases scientific and public interest in the field. The articles address subjects including tactile control, whiskered robots, vibrissal coding, the molecular basis of touch, invertebrate mechanoreception, fingertip transducers and tactile sensing. All the articles in this encyclopedia provide in-depth and state-of-the-art scholarly treatment of the academic topics concerned, making it an excellent reference work for academics, professionals and students.
Haptic perception – human beings’ active sense of touch – is the most complex of human sensory systems, and has taken on growing importance within varied scientific disciplines as well as in practical industrial fields. This book's international team of authors presents the most comprehensive collection of writings on the subject published to date and cover the results of research as well as practical applications. After an introduction to the theory and history of the field, subsequent chapters are dedicated to the neuro-physiological basics as well as the psychological and clinical neuro-psychological aspects of haptic perception.
Active touch can be described as the control of the position and movement of tactile sensing systems to facilitate information gain. In other words, it is finding out about the world by reaching out and exploring—sensing by ‘touching’ as opposed to ‘being touched’. In this Research Topic (with cross-posting in both Behavioural Neuroscience and Neurorobotics) we welcomed articles from junior researchers on any aspect of active touch. We were especially interested in articles on the behavioral, physiological and neuronal underpinnings of active touch in a range of species (including humans) for submission to Frontiers in Behavioural Neuroscience. We also welcomed articles describing robotic systems with biomimetic or bio-inspired tactile sensing systems for publication in Frontiers in Neurorobotics.
An accessible, nontechnical overview of active touch sensing, from sensory receptors in the skin to tactile surfaces on flat screen displays. Haptics, or haptic sensing, refers to the ability to identify and perceive objects through touch. This is active touch, involving exploration of an object with the hand rather than the passive sensing of a vibration or force on the skin. The development of new technologies, including prosthetic hands and tactile surfaces for flat screen displays, depends on our knowledge of haptics. In this volume in the MIT Press Essential Knowledge series, Lynette Jones offers an accessible overview of haptics, or active touch sensing, and its applications. Jones explains that haptics involves integrating information from touch and kinesthesia—that is, information both from sensors in the skin and from sensors in muscles, tendons, and joints. The challenge for technology is to reproduce in a virtual world some of the sensations associated with physical interactions with the environment. Jones maps the building blocks of the tactile system, the receptors in the skin and the skin itself, and how information is processed at this interface with the external world. She describes haptic perception, the processing of haptic information in the brain; haptic illusions, or distorted perceptions of objects and the body itself; tactile and haptic displays, from braille to robotic systems; tactile compensation for other sensory impairments; surface haptics, which creates virtual haptic effects on physical surfaces such as touch screens; and the development of robotic and prosthetic hands that mimic the properties of human hands.
