Tactile Interaction Research Articles

Human–machine collaboration using gesture recognition in mixed reality and robotic fabrication

This research presents an innovative approach that integrated gesture recognition into a Mixed Reality (MR) interface for human–machine collaboration in the quality control, fabrication, and assembly of the Unlog Tower. MR platforms enable users to interact with three-dimensional holographic instructions during the assembly and fabrication of highly custom and parametric architectural constructions without the necessity of two-dimensional drawings. Previous MR fabrication projects have primarily relied on digital menus and custom buttons within the interface for user interaction between virtual and physical environments. Despite this approach being widely adopted, it is limited in its ability to allow for direct human interaction with physical objects to modify fabrication instructions within the virtual environment. The research integrates user interactions with physical objects through real-time gesture recognition as input to modify, update, or generate new digital information. This integration facilitates reciprocal stimuli between the physical and virtual environments, wherein the digital environment is generative of the user’s tactile interaction with physical objects. Thereby providing user with direct, seamless feedback during the fabrication process. Through this method, the research has developed and presents three distinct Gesture-Based Mixed Reality (GBMR) workflows: object localization, object identification, and object calibration. These workflows utilize gesture recognition to enhance the interaction between virtual and physical environments, allowing for precise localization of objects, intuitive identification processes, and accurate calibrations. The results of these methods are demonstrated through a comprehensive case study: the construction of the Unlog Tower, a 36’ tall robotically fabricated timber structure.

Integration of Smart Cane with Social Media: Design of a New Step Counter Algorithm for Cane

This research introduces an innovative smart cane architecture designed to empower visually impaired individuals. Integrating advanced sensors and social media connectivity, the smart cane enhances accessibility and encourages physical activity. Three meticulously developed algorithms ensure accurate step counting, swing detection, and proximity measurement. The smart cane’s architecture comprises the platform, communications, sensors, calculation, and user interface layers, providing comprehensive assistance for visually impaired individuals. Hardware components include an audio–tactile interaction module, input command module, microphone integration, local storage, step count module, cloud integration, and rechargeable battery. Software v1.9.7 components include Facebook Chat API integration, Python Facebook API integration, fbchat library integration, and Speech Recognition library integration. Overall, the proposed smart cane offers a comprehensive solution to enhance mobility, accessibility, and social engagement for visually impaired individuals. This study represents a significant stride toward a more inclusive society, leveraging technology to create meaningful impact in the lives of those with visual impairments. By fostering socialization and independence, our smart cane not only improves mobility but also enhances the overall well-being of the visually impaired community.

DIGITALIZATION OF CLASSICAL LITERARY HERITAGE: ACCESSIBILITY, PERCEPTION, AND INTERPRETATION BY THE NEW GENERATION

The swift ascendance of digital technologies has ushered in a transformative era for the preservation and dissemination of classical literary heritage, presenting both unprecedented opportunities and formidable challenges. This study delves into the nuanced dynamics of digitalization within the realm of classical literature, focusing on three critical aspects: accessibility, perception, and interpretation by the new generation of readers. Employing a mixed-methods research design, the study integrates quantitative surveys and qualitative interviews to comprehensively explore the digital engagement with classical texts among a diverse demographic of readers. The findings illuminate a significant enhancement in the accessibility of classical works through digital platforms, albeit marked by disparities in genre representation and the fidelity of digital reproductions. Moreover, the research uncovers a complex landscape of reader perception, with digital formats fostering a new paradigm of engagement characterized by convenience and interactive exploration, yet sometimes hindered by technological limitations and the loss of tactile interaction. Pertinently, the study reveals a notable shift in the interpretation of classical texts, as digital mediums facilitate collaborative and dynamic interpretive practices among the new generation, diverging from traditional solitary reading experiences. These insights underscore the critical role of digital literacy in shaping the engagement with and understanding of classicalliterature in the digital age. The study’s discussion extends beyond the empirical findings to reflect on the broader implications for educators, librarians, and digital platform developers, advocating for strategic enhancements in digital literary ecosystems to enrich the reader’s experience. In conclusion, the digitalization of classical literary heritage represents a pivotal juncture, offering both challenges and opportunities to reinvigorate the legacy of classical texts for future generations, demanding a concerted effort to harmonize technological advancements with the pedagogical and cultural stewardship of our literary past.

TacSuit: A Wearable Large-Area, Bioinspired Multimodal Tactile Skin for Collaborative Robots

Robots are now working more and more closely with humans outside of traditional fences in industrial scenes. Their real-time tactile interaction perception is crucial to the safety of human–robot collaboration (HRC). In this work, we present a customized, wearable and modular robot skin (TacSuit), which is scalable for large-area surface coverage of robot with easily accessible multi-modal sensors, including pressure, proximity, acceleration and temperature sensors. The TacSuit is co-designed for mechanical structure and data fusion algorithm, consisting of three levels of design: sensor, cell (of multi-modal sensors) and block (of multiple cells). These sensors are stored with custom-designed and 3D printed capsules to achieve the conformity, scalability and easy installation to the arbitrary robot surface. A multi-level event-driven data fusion algorithm enables efficient information processing for large number of tactile sensors. Furthermore, a virtual interaction force fusion method takes both the proximity and force perception information into consideration in order to achieve safety of whole interaction process before and after direct physical contacts. A humanoid robotic platform successfully realizes the TacSuit wear of 159 tactile cells. Validation experiments of obstacle detection demonstrate the effective collision avoidance capability of the TacSuit for safe HRC.

Adaptive tactile interaction transfer via digitally embroidered smart gloves

Human-machine interfaces for capturing, conveying, and sharing tactile information across time and space hold immense potential for healthcare, augmented and virtual reality, human-robot collaboration, and skill development. To realize this potential, such interfaces should be wearable, unobtrusive, and scalable regarding both resolution and body coverage. Taking a step towards this vision, we present a textile-based wearable human-machine interface with integrated tactile sensors and vibrotactile haptic actuators that are digitally designed and rapidly fabricated. We leverage a digital embroidery machine to seamlessly embed piezoresistive force sensors and arrays of vibrotactile actuators into textiles in a customizable, scalable, and modular manner. We use this process to create gloves that can record, reproduce, and transfer tactile interactions. User studies investigate how people perceive the sensations reproduced by our gloves with integrated vibrotactile haptic actuators. To improve the effectiveness of tactile interaction transfer, we develop a machine-learning pipeline that adaptively models how each individual user reacts to haptic sensations and then optimizes haptic feedback parameters. Our interface showcases adaptive tactile interaction transfer through the implementation of three end-to-end systems: alleviating tactile occlusion, guiding people to perform physical skills, and enabling responsive robot teleoperation.

Porous nanocomposites with enhanced intrinsic piezoresistive sensitivity for bioinspired multimodal tactile sensors

In this work, we propose porous fluororubber/thermoplastic urethane nanocomposites (PFTNs) and explore their intrinsic piezoresistive sensitivity to pressure. Our experiments reveal that the intrinsic sensitivity of the PFTN-based sensor to pressure up to 10 kPa increases up to 900% compared to the porous thermoplastic urethane nanocomposite (PTN) counterpart and up to 275% compared to the porous fluororubber nanocomposite (PFN) counterpart. For pressures exceeding 10 kPa, the resistance-pressure relationship of PFTN follows a logarithmic function, and the sensitivity is 221% and 125% higher than that of PTN and PFN, respectively. With the excellent intrinsic sensitivity of the thick PFTN film, a single sensing unit with integrated electrode design can imitate human skin for touch detection, pressure perception and traction sensation. The sensing range of our multimodal tactile sensor reaches ~150 Pa, and it exhibits a linear fit over 97% for both normal pressure and shear force. We also demonstrate that an electronic skin, made of an array of sensing units, is capable of accurately recognizing complex tactile interactions including pinch, spread, and tweak motions.

Vision-based tactile intelligence with soft robotic metamaterial

Robotic metamaterials represent an innovative approach to creating synthetic structures that combine desired material characteristics with embodied intelligence, blurring the boundaries between materials and machinery. Inspired by the functional qualities of biological skin, integrating tactile intelligence into these materials has gained significant interest for research and practical applications. This study introduces a Soft Robotic Metamaterial (SRM) design featuring omnidirectional adaptability and superior tactile sensing, combining vision-based motion tracking and machine learning. The study compares two sensory integration methods to a state-of-the-art motion tracking system and force/torque sensor baseline: an internal-vision design with high frame rates and an external-vision design offering cost-effectiveness. The results demonstrate the internal-vision SRM design achieving an impressive tactile accuracy of 98.96%, enabling soft and adaptive tactile interactions, especially beneficial for dexterous robotic grasping. The external-vision design offers similar performance at a reduced cost and can be adapted for portability, enhancing material science education and robotic learning. This research significantly advances tactile sensing using vision-based motion tracking in soft robotic metamaterials, and the open-source availability on GitHub fosters collaboration and further exploration of this innovative technology (https://github.com/bionicdl-sustech/SoftRoboticTongs).

«АЭЛИТА» ЯКОВА ПРОТАЗАНОВА: МАРС КАК ЧАСТЬ БЕССОЗНАТЕЛЬНОГО ГЕРОЯ-ИНТЕЛЛИГЕНТА 1920-х

The article delves into Yakov Protazanov’s film Aelita (1924), marking its 100th anniversary. It aims to bring to light the nuances of the film, which were overlooked within Soviet film studies, while also highlighting the key differences between Alexei Tolstoy’s original novel and its cinematic adaptation. The Martian storyline, reimagined as the fantastical realm of engineer Mstislav Los by the screenwriters, can be interpreted as the subconscious of the intellectual hero of the 1920s in order to explore its symbolic meaning. The Martian landscape not only embodies governmental conservatism, but, through its constructivist style, symbolizes modernity, a technologically advanced civilization, as well as reflects concerns that come not from the past, but are projected towards the future. The paper analyzes the interplay between the fears and dreams of the intellectual protagonist, whose values were shaped before the 1917 revolution. Unlike his literary counterpart, the screen image of Los has changed: in the film, the engineer is an active man, an adventurer, a person of passion. The ethereal Aelita, the sovereign of Mars, is juxtaposed to Los’ wife, Natasha, a Soviet bureaucrat. While Natasha embodies the democratic ethos of an energetic Soviet woman, Aelita personifies aristocratic ideals. The emotional openness, energetic movements and tactile interactions, and active work and social contacts—the Soviet anthropological ideal—stand in contrast to the personal convictions of Los, who aestheticizes emotional restraint, interpersonal detachment, and social elitism. The article explores the motifs common to the Moscow and Martian storylines: the yearning for interplanetary connections, the need to transcend the usual mode of life in pursuit of something new, different, unattainable, and the willingness to make sacrifices for loftier objectives. In summary, the screenwriters have radically transformed the world of Tolstoy’s novel, which manifests the impotence of an individual in the face of revolutionary turmoil and emotional depression over the loss of a beloved one. Protazanov’s film underscores the importance of active participation of not only the Red Army soldier (Gusev), but also the intellectual (Los). While aligning with certain tenets of Soviet ideology, the film also contains subtexts that challenge it. Such is the (imaginary) revolution on Mars, which turns out to be driven not by a collective awakening among the working people of Mars, but rather by the individualistic ambitions of two Earthly men: the inertia of soldier Gusev’s ardor and the jealousy of intellectual Los, his detachment from with his Soviet wife and his yearning for emotional and erotic solace with a woman of royal lineage. The article surveys critical and theoretical analyses (both domestic and international) on Aelita, revealing motifs resonant with the Western European cinematic trends of the 1920s and of subsequent decades, from auteur (Robert Wiene, Fritz Lang, Andrei Tarkovsky) to popular science fiction films and series of the early 21st century (Cloud Atlas, Dune, Foundation, etc.). This reconfirms the scale of Protazanov’s Aelita, its predictive potential and artistic merit within the tapestry of global cinema.

An integrative taxonomic approach to the Atlantic Hansarsia (formerly Nematoscelis) yields new krill taxa (Crustacea: Euphausiidae)

A recent molecular phylogenetic and biogeographic study on the krill genus Hansarsia revealed undescribed cryptic diversity in the Atlantic. Each of four species analysed encompassed robust molecular clades that were linked to dimorphic males in H. microps, H. atlantica and H. tenella. We tested the robustness and divergence of the observed clades using an integrative approach including (1) three independent species delimitation methods for the mitochondrial COI gene (ASAP, GMYC, bPTP), (2) variability of two nuclear genes (H3 and ITS1) and (3) morphological analysis (MDS and PCA) with a dataset of 22 characters scored for 131 specimens. Both molecular and morphological analyses resulted in at least six distinct clades within the Atlantic Hansarsia. The strongest divergence was revealed between the two clades of H. tenella, one of which we diagnosed as a new species. Two clades of H. megalops also showed significant divergence but in the absence of males, we were reluctant to designate new species. Different clades linked to male forms in H. microps and H. atlantica are suggested as an incipient species. We also hypothesise an unusual trend in the evolution of euphausiids, in which visual recognition enhances tactile interaction during mating. Our results show that analyses of ostensibly well studied groups may yet yield taxonomic surprises. ZooBank: urn:lsid:zoobank.org:pub:AE045636-50EF-450A-B9B3-9231E8B91522

To touch or to be touched? comparing appraisal of vicarious execution and reception of interpersonal touch.

Unmyelinated C-Tactile (CT) fibres are activated by caress-like touch, eliciting a pleasant feeling that decreases for static and faster stroking. Previous studies documented this effect also for vicarious touch, hypothesising simulation mechanisms driving the perception and appreciation of observed interpersonal touch. Notably, less is known about appreciation of vicarious execution of touch, that is as referred to the one giving gentle touch. To address this issue, 53 healthy participants were asked to view and rate a series of videoclips displaying an individual being touched by another on hairy (i.e., hand dorsum) or glabrous (i.e., palm) skin sites, with touch being delivered at CT-optimal (5 cm/s) or non-CT optimal velocities (0 cm/s or 30 cm/s). Following the observation of each clip, participants were asked to rate self-referred desirability and model-referred pleasantness of vicarious touch for both executer (toucher-referred) and receiver (touchee-referred). Consistent with the CT fibres properties, for both self-referred desirability and model-referred pleasantness judgements of vicarious touch execution and reception, participants provided higher ratings for vicarious touch delivered at CT-optimal than other velocities, and when observed CT-optimal touch was delivered to the hand-dorsum compared to the palm. However, higher ratings were attributed to vicarious reception compared to execution of CT-optimal touch. Notably, individual differences in interoceptive trusting and attitude to interpersonal touch were positively correlated with, respectively, toucher- and touchee-related overall appraisal ratings of touch. These findings suggest that the appreciation of both toucher- and touchee-referred vicarious touch is specifically attuned to CT-optimal touch, even though they might rely on different neurocognitive mechanisms to understand affective information conveyed by interpersonal tactile interactions.

Tracking Object’s Pose via Dynamic Tactile Interaction

It is a challenging task to localize and track an in-hand object in robotic domain. Researchers were mainly using the vision as major modality for extracting object’s pose. The vision approaches are fragile when the object is occluded by the robotic arm and hand. To this end, we propose a tactile-based DTI-Tracker (tracking object’s pose via Dynamic Tactile Interaction) approach and formalize the object’s tracking as a filter problem. An Extended Kalman Filter (EKF) is used to estimate the in-hand object pose exploiting the high spatial resolution tactile feedback. Given the initial estimation error, the proposed approach rapidly converges the estimation result to the real pose and the statistic evaluation shows the robustness of the proposed approach. We evaluate this method in physics simulation and real multi-fingered grasping setup while the object is static and movable. The proposed method is a potential tool to foster future research on dexterous manipulation using multifingered robotic hand.

Omnidirectionally Strain‐Unperturbed Tactile Array from Modulus Regulation in Quasi‐Homogeneous Elastomer Meshes

AbstractSkin‐like stretchable tactile arrays are of paramount significance for perceiving physical interactions in dynamic biological tissues, prosthetic limbs, and robots. However, mechanical strain‐induced interference invariably degrades the pressure‐sensing accuracy of tactile arrays. In this work, an omnidirectionally strain‐unperturbed tactile array is prepared through modulus regulation in quasi‐homogeneous elastomer meshes. By varying fiber orientations, the proportion of intrinsic elastic and structural deformations in quasi‐homogeneous elastomer meshes can be adjusted, and the modulus can be regulated from 0.23 to 8.23 MPa. The tactile array combined with low‐ and high‐modulus elastomer meshes enables strain‐unperturbed pressure sensing through local stiffening and controllable deformation. Remarkably, the tactile array exhibits 97% strain insensitivity when stretched 100% along the omniplane directions. Moreover, the quasi‐homogeneous structure endows the tactile array with high robustness, even after 5000 cycles of severe stretching or pressing. By integrating the tactile array with a microcontroller, a tactile visualization system is built to achieve accurate tactile interaction even under multiaxial tensile strain. This work provides an alternative insight into the design of omnidirectionally strain‐unperturbed electronic devices for wide applications on dynamic surfaces.

Sound-vibration: Relations between bodies, low frequencies, and multisensory experiments

Multimodality research has enabled academics to propose and support new ideas in multiple modes for interpretation, communication, and as an important part of art education. In this piece, multimodal listening is situated as a transcendence of ear-centric approaches and the use of vibration as a poetic practice in contemporary art. As a result, sonic arts and sound experience principles are used to talk about everyday sounds in new and immersive ways, encouraging the audience to disrupt established sensorial boundaries. Subsequently, sound-vibration can be interrelated as a mode of multimodality and as a resource for meaning-making in possible contemporary practices. If perception is considered multifaceted, one could notice the world as an integration of conscious or unaware inputs. In the experience of sound installations, one may explore oscillations as a valuable channel for understanding multimodal approaches since, unlike visual or tactile interactions, the relationship between sound and the body hinges on fully embodied situations. The underlying thought in this piece will emerge from two recent art pieces, that produce atmospheres and blur the concrete division of senses, transversely representing the potential of the low frequencies.

Role ofmedial prefrontal cortex andprimary somatosensory cortex inself andother-directed vicarious social touch: a TMS study.

Conflicting evidence points to the contribution of several key nodes of the 'social brain' to the processing of both discriminatory and affective qualities of interpersonal touch. Whether the primary somatosensory cortex (S1) and the medial prefrontal cortex (mPFC), two brain areas vital for tactile mirroring and affective mentalizing, play a functional role in shared representations of C-tactile (CT) targeted affective touch is still a matter of debate. Here, we used offline continuous theta-burst transcranial magnetic stimulation (cTBS) to mPFC, S1 and vertex (control) prior to participants providing ratings of vicarious touch pleasantness for self and others delivered across several body sites at CT-targeted velocities. We found that S1-cTBS led to a significant increase in touch ratings to the self, with this effect being positively associated to levels of interoceptive awareness. Conversely, mPFC-cTBS reduced pleasantness ratings for touch to another person. These effects were not specific for CT-optimal (slow) stroking velocities, but rather they applied to all types of social touch. Overall, our findings challenge the causal role of the S1 and mPFC in vicarious affective touch and suggest that self- vs other-directed vicarious touch responses might crucially depend on the specific involvement of key social networks in gentle tactile interactions.

Robust and Flexible Sliding Tactile Sensor for Surface Pattern Perception and Recognition

Perceiving surface characteristics through tactile interaction typically requires high‐resolution devices or precise spatial scanning to record and analyze a significant amount of information. However, most available tactile sensors require complicated technological processes, redundant layouts, and data acquisition circuits, which limits their ability to provide a real‐time static perception and feedback for potential applications such as robotic manipulation. Drawing inspiration from the sliding tactile (ST) perception mode of the human fingertip, a robust and flexible ST sensor with a low array density of 2.7 cells cm−2 is reported. This innovative sensor has a soft and cambered configuration that allows it to rapidly and accurately recognize the 3D surface features of objects, including grooves as small as 500 μm. Benefiting from the strong correlation between collected electronic responding and local deformation of sensing cell, the ST sensor can adaptively reconstruct surface patterns with the assistance of deep learning, even on unstructured objects. The pattern recognition system based on the robot is demonstrated by accurately classifying a set of mahjong tiles with nearly 100% accuracy, surpassing human tactile perception capabilities in the same task.

A platypus-inspired electro-mechanosensory finger for remote control and tactile sensing

Advancement in human-robot interaction (HRI) is essential for the development of intelligent robots, but there lack paradigms to integrate remote control and tactile sensing for an ideal HRI. In this study, inspired by the platypus beak sense, we propose a bionic electro-mechanosensory finger (EM-Finger) synergizing triboelectric and visuotactile sensing for remote control and tactile perception. A triboelectric sensor array made of a patterned liquid-metal-polymer conductive (LMPC) layer encodes both touchless and tactile interactions with external objects into voltage signals in the air, and responds to electrical stimuli underwater for amphibious wireless communication. Besides, a three-dimensional finger-shaped visuotactile sensing system with the same LMPC layer as a reflector measures contact-induced deformation through marker detection and tracking methods. A bioinspired bimodal deep learning algorithm implements data fusion of triboelectric and visuotactile signals and achieves the classification of 18 common material types under varying contact forces with an accuracy of 94.4 %. The amphibious wireless communication capability of the triboelectric sensor array enables touchless HRI in the air and underwater, even in the presence of obstacles, while the whole system realizes high-resolution tactile sensing. By naturally integrating remote contorl and tactile sensing, the proposed EM-Finger could pave the way for enhanced HRI in machine intelligence.

Topography and relationship-specific social touching in individuals displaying body image disturbances

Interpersonal touch is intimately related to the emotional bond between the touch giver and the touch receiver. Which bodily regions we touch in those individuals in our social network is relationship specific. Perception of interpersonal touch is altered in psychiatric disorders characterised by body image disturbances (BIDs). Here, we examined whether the ‘imagined’ experience of social touch in individuals with BIDs is body topography- and relationship-specific. By using an interactive media mobile App, the Virtual Touch Toolkit, high versus low levels of BIDs participants completed heatmaps of full-body virtual avatars, to indicate the body regions they find soothing/unpleasant to be touched by a loved one versus an acquaintance. Self-reports of interoceptive awareness and dysmorphic concerns were also measured. Overall, imagined touch was rated as the most soothing when received from a loved one, and also when this was delivered to ‘social’ body regions. The importance of the social relationship for the imagined tactile interactions was particularly evident for the high levels of BIDs group, with greater problems with interoceptive awareness predicting higher soothing touch ratings when this was received by a loved one. Despite the evidence that imagined bodily contacts between meaningful people is the most pleasant for socially acceptable bodily regions, our findings may suggest a greater sensitivity to relation-specific bodily patterns of social touch particularly in the high level of BIDs group. Heightened interoceptive awareness may also play a key role in this experience of bodily affective contacts. Future research for body-oriented therapy for BIDs is encouraged to systematically probe the efficacy of imagined social touch interaction protocols which use more plausible, ecological, scenarios where touch is delivered by loved ones and to socially acceptable bodily regions.

Design and Evaluation of CPR Emergency Equipment for Non-Professionals.

Sudden cardiac death is a sudden and highly fatal condition. Implementing high-quality emergency cardiopulmonary resuscitation (CPR) early on is an effective rescue method for this disease. However, the rescue steps of CPR are complicated and difficult to remember, and the quantitative indicators are difficult to control, which leads to a poor quality of CPR emergency actions outside the hospital setting. Therefore, we have developed CPR emergency equipment with a multisensory feedback function, aiming to guide rescuers in performing CPR through visual, auditory, and tactile interaction. This equipment consists of three components: first aid clothing, an audio-visual integrated terminal, and a vital sign detector. These three components are based on a micro-power WiFi-Mesh network, enabling the long-term wireless transmission of the multisensor data. To evaluate the impact of the multisensory feedback CPR emergency equipment on nonprofessionals, we conducted a controlled experiment involving 32 nonmedical subjects. Each subject was assigned to either the experimental group, which used the equipment, or the control group, which did not. The main evaluation criteria were the chest compression (CC) depth, the CC rate, the precise depth of the CC ratio (5-6 cm), and the precise rate of the CC ratio -(100-120 times/min). The results indicated that the average CC depth in the experimental group was 51.5 ± 1.3 mm, which was significantly better than that of the control group (50.2 ± 2.2 mm, p = 0.012). Moreover, the average CC rate in the experimental group (110.1 ± 6.2 times/min) was significantly higher than that of the control group (100.4 ± 6.6 times/min) (p < 0.001). Compared to the control group (66.37%), the experimental group showed a higher proportion of precise CC depth (82.11%), which is closer to the standard CPR rate of 100%. In addition, the CC ratio of the precise rate was 93.75% in the experimental group, which was significantly better than that of 56.52% in the control group (p = 0.024). Following the experiment, the revised System Availability Scale (SUS) was utilized to evaluate the equipment's usability. The average total SUS score was 78.594, indicating that the equipment's acceptability range was evaluated as 'acceptable', and the overall adjective rating was 'good'. In conclusion, the multisensory feedback CPR emergency equipment significantly enhances the CC performance (CC depth, CC rate, the precise depth of CC ratio, the precise rate of CC ratio) of nonprofessionals during CPR, and the majority of participants perceive the equipment as being easy to use.

Touch-and-Heal

Affective touch plays an important role in human-robot interaction. However, it is challenging for robots to perceive various natural human tactile gestures accurately, and feedback human intentions properly. In this paper, we propose a data-driven affective computing system based on a biomimetic quadruped robot with large-format, high-density flexible pressure sensors, which can mimic the natural tactile interaction between humans and pet dogs. We collect 208-minute videos from 26 participates and construct a dataset of 1212 human gestures-dog actions interaction sequences. The dataset is manually annotated with an 81-tactile-gesture vocabulary and a 44-corresponding-dog-reaction vocabulary, which are constructed through literature, questionnaire, and video observation. Then, we propose a deep learning algorithm pipeline with a gesture classification algorithm based on ResNet and an action prediction algorithm based on Transformer, which achieve the classification accuracy of 99.1% and the 1-gram BLEU score of 0.87 respectively. Finally, we conduct a field study to evaluate the emotion regulation effects through tactile affective interaction, and compare it with voice interaction. The results show that our system with tactile interaction plays a significant role in alleviating user anxiety, stimulating user excitement and improving the acceptability of robotic dogs.

Behavioural Models of Risk-Taking in Human-Robot Tactile Interactions.

Touch can have a strong effect on interactions between people, and as such, it is expected to be important to the interactions people have with robots. In an earlier work, we showed that the intensity of tactile interaction with a robot can change how much people are willing to take risks. This study further develops our understanding of the relationship between human risk-taking behaviour, the physiological responses by the user, and the intensity of the tactile interaction with a social robot. We used data collected with physiological sensors during the playing of a risk-taking game (the Balloon Analogue Risk Task, or BART). The results of a mixed-effects model were used as a baseline to predict risk-taking propensity from physiological measures, and these results were further improved through the use of two machine learning techniques-support vector regression (SVR) and multi-input convolutional multihead attention (MCMA)-to achieve low-latency risk-taking behaviour prediction during human-robot tactile interaction. The performance of the models was evaluated based on mean absolute error (MAE), root mean squared error (RMSE), and R squared score (R2), which obtained the optimal result with MCMA yielding an MAE of 3.17, an RMSE of 4.38, and an R2 of 0.93 compared with the baseline of 10.97 MAE, 14.73 RMSE, and 0.30 R2. The results of this study offer new insights into the interplay between physiological data and the intensity of risk-taking behaviour in predicting human risk-taking behaviour during human-robot tactile interactions. This work illustrates that physiological activation and the intensity of tactile interaction play a prominent role in risk processing during human-robot tactile interaction and demonstrates that it is feasible to use human physiological data and behavioural data to predict risk-taking behaviour in human-robot tactile interaction.