Search results

This paper aims to improve the diversity and richness of haptic perception by recognizing multi-modal haptic images.

First, the multi-modal haptic data collected by BioTac sensors from different objects are pre-processed, and then combined into haptic images. Second, a multi-class and multi-label deep learning model is designed, which can simultaneously learn four haptic features (hardness, thermal conductivity, roughness and texture) from the haptic images, and recognize objects based on these features. The haptic images with different dimensions and modalities are provided for testing the recognition performance of this model.

The results imply that multi-modal data fusion has a better performance than single-modal data on tactile understanding, and the haptic images with larger dimension are conducive to more accurate haptic measurement.

The proposed method has important potential application in unknown environment perception, dexterous grasping manipulation and other intelligent robotics domains.

This paper proposes a new deep learning model for extracting multiple haptic features and recognizing objects from multi-modal haptic images.

This paper aims to examine how visual and haptic package design characteristics singularly and jointly affect consumers' brand impressions.

Integrating and extending design perception with congruence and fluency theories, the paper presents three research propositions that are tested in three studies. Bottled water serves as an example category with data provided by professionals and consumers.

Study 1 identifies key types of holistic bimodal designs (Modern, Big Grip, Prototypical‐Small, Boxy Billboards, and Prototypical‐Large) based on brand visual and haptic factors. Study 2 relates these types to unique single‐modal brand impressions. Study 3 determines how consumers evaluate brands depending on the semantic congruence between haptics and visuals. Except for the excitement dimension, brand evaluations are more positive under conditions of high rather than low congruence.

The findings are obtained for a single category (bottled water) using experiments designed to highlight and focus consumer attention on the formation of impressions. The findings may thus not fully reflect consumer responses in actual retail purchase situations.

The paper provides preliminary guidelines on how to utilize visual and haptic cues in the design of brand packages for stimulating desired consumer responses.

The work presented in this paper contributes to the literature on design‐based brand inferences and semantic congruence by integrating the visual with the haptic perspectives.

Virtual reality (VR) for product assembly has been studied for more than 20 years but its practical application in industry is still very much in its infancy. Haptics is a new and important interaction method for VR and a strong and growing research area, however, it still remains a virtually unknown concept for industrial application.

This paper provides a comprehensive survey of VR and haptics for product assembly, from rigid parts to soft cables.

Some new ideas and research progresses in recent years are especially investigated. First the concepts and classifications of virtual assembly are introduced and the different virtual environment systems for product assembly are discussed. Then the major research groups, typical systems and major research issues are explored in detail, treating rigid parts and soft cables separately. Lastly, the barriers preventing successful application of virtual assembly are discussed and future research directions are also summarized.

The paper provides an overview and analysis of VR and haptics for product assembly, including both rigid parts and soft cables.

Development of autonomous robot manipulator for human-robot assembly tasks is a key component to reach high effectiveness. In such tasks, the robot real-time object recognition is crucial. In addition, the need for simple and safe teaching techniques need to be considered, because: small size robot manipulators’ presence in everyday life environments is increasing requiring non-expert operators to teach the robot; and in small size applications, the operator has to teach several different motions in a short time.

For object recognition, the authors propose a deep belief neural network (DBNN)-based approach. The captured camera image is used as the input of the DBNN. The DBNN extracts the object features in the intermediate layers. In addition, the authors developed three teaching systems which utilize iPhone; haptic; and Kinect devices.

The object recognition by DBNN is robust for real-time applications. The robot picks up the object required by the user and places it in the target location. Three developed teaching systems are easy to use by non-experienced subjects, and they show different performance in terms of time to complete the task and accuracy.

The proposed method can ease the use of robot manipulators helping non-experienced users completing different assembly tasks.

This work applies DBNN for object recognition and three intuitive systems for teaching robot manipulators.

The paper aims to present the processing pipeline of an assembly immersive simulation application which can manage the interaction between the virtual scene and user using stereoscopic display and haptic devices. A new set of elements are integrated in a Collaborative Virtual Environment (CVE) and validated using an approach based on subjective and objective users’ performance criteria. The developed application is intended for Assembly/Disassembly (A/D) analysis, planning and training.

A mobility module based on contact information is used to handle the assembly components’ movements through real-time management of collision detection and kinematically constraint guidance. Information on CVE architecture, modules and application configuration process are presented. Impact of device type (3 degrees of freedom (DoFs) vs 6 DoFs) over user’s experience is evaluated. Parameters (number of assembled components and components assembly time) are measured for each user and each haptic device, and results are compared and discussed.

Test results proved the efficiency of using a mobility module based on predefined kinematic constraints for reducing the complexity of collision detection algorithms in real-time assembly haptic simulations. Also, experiments showed that, generally, users performed better with 3 DoFs haptic device compared to 6 DoFs haptic equipment.

The proposed immersive application automates the kinematical joints inference from 3D computer-aided design (CAD) assembly models and integrates it within a haptic-based virtual environment, for increasing the efficiency of A/D process simulations.

This chapter reports on research that explores new and emerging extended reality [XR] technologies and how they might provide opportunities to trial, investigate, and put into practice their potential to reverse processes of atomisation, polarisation, and intercultural discomfort, in our contemporary society. This transdisciplinary practice-led research was underpinned by disciplines of computer science and engineering, social sciences, history, diverse community economics, human ecology, and Indigenous psychology. The collaboration between these various disciplines with the Māori and non-Māori community members allowed researchers to understand current societal stressors, prioritise relationality, and explore our shared values in the creation of XR experiences for exhibition in the galleries, libraries, archives, and museums [GLAM] sector.

A discursive design framework motivated, inspired, provoked, persuaded, and reminded inspiring collaborators, and visitors to the exhibitions, the value of (re)connecting with people and overcoming interracial awkwardness through these curated experiences. The XR technologies provided women a platform to discuss and reimagine first encounters between people from different cultural backgrounds. The technologies included a 180° stereoscopic projection, Common Sense, in which Māori Elder Irene Hancy shared her insight about social engagement and haptic HONGI in which visitors were greeted by a Māori woman Tania Remana via augmented reality. This research has been motivated by a desire to promote and support intercultural understanding in Aotearoa New Zealand, and it extends research by other non-Māori and Māori scholars.

Hot‐cells are shielded structures protecting individuals from radioactive materials. The purpose of this paper is to propose a design approach for a hot‐cell simulator using digital mock‐up (DMU) technology and combining Haptic guided complex robotic manipulation for assembly tasks in a virtual environment.

The principal reason for developing a simulator was to explore the feasibility of hot‐cell structure design and collision‐free assembly process. For this, a simulation design philosophy has been proposed that includes DMU facility offering the ability of analyzing the operations and performing complex robotic manipulations in the virtual hot‐cell environment. Furthermore, enhanced Haptic mapping for tele‐manipulation is proposed for training and guidance purposes.

From the analysis and task scenarios performed in virtual simulator, the optimal positions of the manipulators and need of (bridge transport dual arm servo‐manipulators) type were identified. Operation tasks were performed remotely using virtual hot‐cell technology by simulating the scenarios in the DMU reducing the overall operation cost and user training. The graphic simulator substantially reduced the cost of the process and maintenance procedure as well as the process equipment by providing a pre‐analysis of whole scenario for real manipulation.

This research tries to contribute to the virtual hot‐cell design philosophy. Tele‐operated complex robotic operations in DMU technology are performed in virtual hot‐cell. The simulator provides improved Haptic guidance with force and torque feedback enhancing the realism of virtual environment.

This paper aims to illustrate the increasingly important role played by tactile sensing in robotics by considering three specific fields of application.

Following a short introduction, this paper first provides details of tactile sensing principles, technologies, products and research. The following sections consider tactile sensing applications in robotic surgery, collaborative robots and robotic grippers. Finally, brief conclusions are drawn.

Tactile sensors are the topic of an extensive and technologically diverse research effort, with sensing skins attracting particular attention. Many products are now available commercially. New generations of surgical robots are emerging which use tactile sensing to provide haptic feedback, thereby eliminating the surgeon’s total reliance on visual control. Many collaborative robots use tactile and proximity sensing as key safety mechanisms and some use sensing skins. Some skins can detect both human proximity and physical contact. Sensing skins that can be retrofitted have been developed. Commercial tactile sensors have been incorporated into robotic grippers, notably anthropomorphic types, and allow the handling of delicate objects and those with varying shapes and sizes. Tactile sensing uses will inevitably increase because of the ever-growing numbers of robots interacting with humans.

This study provides a detailed account of the growing use of tactile sensing in robotics in three key areas of application.

Haptic interfaces enable person‐machine communication through touch, and most commonly, in response to user movements. We comment on a distinct property of haptic interfaces, that of providing for simultaneous information exchange between a user and a machine. We also comment on the fact that, like other kinds of displays, they can take advantage of both the strengths and the limitations of human perception. The paper then proceeds with a description of the components and the modus operandi of haptic interfaces, followed by a list of current and prospective applications and a discussion of a cross‐section of current device designs.

The purpose of this paper is to give a comprehensive survey on the physics-based virtual assembly (PBVA) technology in a novel perspective, to analyze current drawbacks and propose several promising future directions.

To provide a deep insight of PBVA, a discussion of the developing context of PBVA and a comparison against constraint-based virtual assembly (CBVA) is put forward. The core elements and general structure are analyzed based on typical PBVA systems. Some common key issues as well as common drawbacks are discussed, based on which the research trend and several promising future directions are proposed.

Special attention is paid to new research progresses and new ideas concerning recent development as well as new typical systems of the technology. Advantages of PBVA over CBVA are investigated. Based on the analysis of typical PBVA systems and the evolution of PBVA, the core elements of the technology and the general structure of its implementation are identified. Then, current PBVA systems are summarized and classified. After that, key issues in the technology and current drawbacks are explored in detail. Finally, promising future directions are given, including both the further perfecting of the technology and the combination with other technologies.

The PBVA technology is put into a detailed review and analysis in a novel way, providing a better insight of both the theory and the implementation of the technology.