Robot Interaction Research Articles

The Perception of Agency

The perception of agency in human robot interaction has become increasingly important as robots become more capable and more social. There are, however, no accepted or consistent methods of measuring perceived agency; researchers currently use a wide range of techniques and surveys. We provide a definition of perceived agency, and from that definition we create and psychometrically validate a scale to measure perceived agency. We then perform a scale evaluation by comparing the PA scale constructed in experiment 1 to two other existing scales. We find that our PA and PA-R (Perceived Agency–Rasch) scales provide a better fit to empirical data than existing measures. We also perform scale validation by showing that our scale shows the hypothesized relationship between perceived agency and morality.

Examining the relationship between firm characteristics and Industry 4.0 technology adoption in Vietnam's apparel industry

ABSTRACT This study investigates the relationships between firm characteristics (region, firm size, firm age, and product category) and Industry 4.0 technology adoption in the Vietnamese apparel manufacturing industry. As the key Industry 4.0 technologies, Artificial Intelligence (AI), Interactive Robotics, Smart Sensors, Big Data, 3D Printing, physical Cyber-Physical Systems (CPS), and human-robot interaction were included to examine technology adoption. The hypotheses were tested using a series of Chi-square analyses with data gathered from 210 Vietnamese apparel-manufacturing firms. The results indicate no clear pattern of associations between firm characteristics and technology adoption and provide empirical support for firms’ strategic adoption of a certain set of Industry 4.0 technologies in line with their firm characteristics. On the other hand, the findings from scatter charts indicated that AI, Interactive Robotics, and 3D Printing are three key technologies that apparel firms applied the most and at a similar level.

Understanding human–robot interaction forces: a new mechanical solution

Nowadays, robots hold crucial roles in an increasing number of different fields, highlighting an ongoing transition to ever-closer collaboration between humans and machines. In this context, this new technological era has brought out safety issues and, consequently, robots need to be monitored with an appropriate control architecture and human–machine interaction forces should be correctly estimated. For this purpose, friction, inertia, external perturbation, and the intrinsic dynamic of the robots should be monitored. This specific work starts from the need to monitor human–robot interaction forces to ensure safety for users. A successful case study concerning the integration of additional sensors on a wrist robot that directly interacts with humans is shown. Its limits have been the inability to directly measure forces applied by users and the impossibility to know accurately the end-effector position. Firstly, introducing a force/torque sensor, the detection of the forces applied by the user to the robot has been enabled. The user’s force data have been used to measure force dissipation and, together with the smoothness of operation, to compare three different embeddable mechanisms. Moreover, the integration of a linear encoder allowed measuring the instantaneous end-effector position on a non-actuated linear guideway, consequently knowing the motor torque value and the force applied by the robot to the user. This has been compared to the interaction force estimated from the motor torques without the linear sensor. The error assessed between the force measured with the encoder and estimated without it is about 12.9%. These results demonstrate the importance of this new embedded system to detect human–machine interaction forces in an accurate way and prevent safety issues.

Correction to: Gendered Human–Robot Interactions in Services

Correction to: Gendered Human–Robot Interactions in Services

A novel tactile sensor with multimodal vision and tactile units for multifunctional robot interaction

AbstractRobots with multi-sensors always have a problem of weak pairing among different modals of the collected information produced by multi-sensors, which leads to a bad perception performance during robot interaction. To solve this problem, this paper proposes a Force Vision Sight (FVSight) sensor, which utilizes a distributed flexible tactile sensing array integrated with a vision unit. This innovative approach aims to enhance the overall perceptual capabilities for object recognition. The core idea is using one perceptual layer to trigger both tactile images and force-tactile arrays. It allows the two heterogeneous tactile modal information to be consistent in the temporal and spatial dimensions, thus solving the problem of weak pairing between visual and tactile data. Two experiments are specially designed, namely object classification and slip detection. A dataset containing 27 objects with deep presses and shallow presses is collected for classification, and then 20 slip experiments on three objects are conducted. The determination of slip and stationary state is accurately obtained by covariance operation on the tactile data. The experimental results show the reliability of generated multimodal data and the effectiveness of our proposed FVSight sensor.

Got It? Comparative Ergonomic Evaluation of Robotic Object Handover for Visually Impaired and Sighted Users

The rapidly growing research on the accessibility of digital technologies has focused on blind or visually impaired (BVI) users. However, the field of human–robot interaction has largely neglected the needs of BVI users despite the increasing integration of assistive robots into daily life and their potential benefits for our aging societies. One basic robotic capability is object handover. Robots assisting BVI users should be able to coordinate handovers without eye contact. This study gathered insights on the usability of human–robot handovers, including 20 BVI and 20 sighted participants. In a standardized experiment with a mixed design, a handover robot prototype equipped with a voice user interface and haptic feedback was evaluated. The robot handed over everyday objects (i) by placing them on a table and (ii) by allowing for midair grasping. The usability target was met, and all user groups reported a positive user experience. In total, 97.3% of all handovers were successful. The qualitative feedback showed an appreciation for the clear communication of the robot’s actions and the handover reliability. However, the duration of the handover was seen as a critical issue. According to all subjective criteria, the BVI participants showed higher variances compared to the sighted participants. Design recommendations for improving robotic handovers equally supporting both user groups are given.

System software architecture for advancing human robot interaction by cloud services and multi-robot cooperation

Human-like interactions with robots based on Conversational AI facilitate assistance and teamwork in various contexts. Those interactions are further enhanced by utilizing physical presence and context from the robot's hardware. Robot cooperation is also especially useful, when software or hardware resources have to be shared in a multi-robot system. Therefore, we propose a modular software architecture for multi-robot cooperation that extends the integration of Conversational AI into Socially Assistive Robots, previously suggested by authors. It utilizes a flow-based approach that involves shared repositories and direct or message-driven communication to convey natural language transcriptions among robots in order to support their cooperation. By experiments we evaluated the cooperation between NAOqi based robots and Furhat robot. Our experimental results demonstrate architecture's modularity and adaptability to different cloud services, along with its effectiveness for interactions involving multiple robots.

Co-existing with Drones: A Virtual Exploration of Proxemic Behaviours and Users’ Insights on Social Drones

Numerous studies have investigated proxemics in the context of human–robot interactions, but little is known about whether these insights can be applied to human–drone interactions (HDI). As drones become more common in social settings, it is crucial to ensure they navigate in a socially acceptable and human-friendly way. Understanding how individuals position themselves around drones is vital to promote user well-being and drones’ social acceptance. However, real-world constraints and risks associated with drones flying in close proximity to participants have limited research in this field. Virtual reality is a promising alternative for investigating HDI, as prior research suggests. This paper presents a proxemic user study (N = 45) in virtual reality, examining how drone height and framing influence participants’ proxemic preferences. The study also explores participants’ perceptions of social drones and their vision for the future of flying robots. Our findings show that drone height significantly impacts participants’ preferred interpersonal distance, while framing had no significant effect. Thoughts on how participants envision social drones (e.g., interaction, design, applications) reveal interpersonal differences but also shows overall consistency over time. While the study demonstrates the value of using virtual reality for HDI experiments, further research is necessary to determine the generalizability of our findings to real-world HDI scenarios.

Previous Experience Matters: An in-Person Investigation of Expectations in Human–Robot Interaction

The human–robot interaction (HRI) field goes beyond the mere technical aspects of developing robots, often investigating how humans perceive robots. Human perceptions and behavior are determined, in part, by expectations. Given the impact of expectations on behavior, it is important to understand what expectations individuals bring into HRI settings and how those expectations may affect their interactions with the robot over time. For many people, social robots are not a common part of their experiences, thus any expectations they have of social robots are likely shaped by other sources. As a result, individual expectations coming into HRI settings may be highly variable. Although there has been some recent interest in expectations within the field, there is an overall lack of empirical investigation into its impacts on HRI, especially in-person robot interactions. To this end, a within-subject in-person study (N=31\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$N=31$$\\end{document}) was performed where participants were instructed to engage in open conversation with the social robot Pepper during two 2.5 min sessions. The robot was equipped with a custom dialogue system based on the GPT-3 large language model, allowing autonomous responses to verbal input. Participants’ affective changes towards the robot were assessed using three questionnaires, NARS, RAS, commonly used in HRI studies, and Closeness, based on the IOS scale. In addition to the three standard questionnaires, a custom question was administered to capture participants’ views on robot capabilities. All measures were collected three times, before the interaction with the robot, after the first interaction with the robot, and after the second interaction with the robot. Results revealed that participants to large degrees stayed with the expectations they had coming into the study, and in contrast to our hypothesis, none of the measured scales moved towards a common mean. Moreover, previous experience with robots was revealed to be a major factor of how participants experienced the robot in the study. These results could be interpreted as implying that expectations of robots are to large degrees decided before interactions with the robot, and that these expectations do not necessarily change as a result of the interaction. Results reveal a strong connection to how expectations are studied in social psychology and human-human interaction, underpinning its relevance for HRI research.

Modelling and Measuring Trust in Human–Robot Collaboration

Recognizing trust as a pivotal element for success within Human–Robot Collaboration (HRC) environments, this article examines its nature, exploring the different dimensions of trust, analysing the factors affecting each of them, and proposing alternatives for trust measurement. To do so, we designed an experimental procedure involving 50 participants interacting with a modified ‘Inspector game’ while we monitored their brain, electrodermal, respiratory, and ocular activities. This procedure allowed us to map dispositional (static individual baseline) and learned (dynamic, based on prior interactions) dimensions of trust, considering both demographic and psychophysiological aspects. Our findings challenge traditional assumptions regarding the dispositional dimension of trust and establish clear evidence that the first interactions are critical for the trust-building process and the temporal evolution of trust. By identifying more significant psychophysiological features for trust detection and underscoring the importance of individualized trust assessment, this research contributes to understanding the nature of trust in HRC. Such insights are crucial for enabling more seamless human–robot interaction in collaborative environments.

A Psychological Need-Fulfillment Perspective for Designing Social Robots that Support Well-Being

This conceptual paper presents a novel framework for the design and study of social robots that support well-being. Building upon the self-determination theory and the associated Motivation, Engagement, and Thriving in User Experience (METUX) model, this paper argues that users’ psychological basic needs for autonomy, competence, and relatedness should be put at the center of social robot design. These basic needs are essential to people’s psychological well-being, engagement, and self-motivation. However, current literature offers limited insights into how human–robot interactions are related to users’ experiences of the satisfaction of their basic psychological needs and thus, to their well-being and flourishing. We propose that a need-fulfillment perspective could be an inspiring lens for the design of social robots, including socially assistive robots. We conceptualize various ways in which a psychological need-fulfillment perspective may be incorporated into future human–robot interaction research and design, ranging from the interface level to the specific tasks performed by a robot or the user’s behavior supported by the robot. The paper discusses the implications of the framework for designing social robots that promote well-being, as well as the implications for future research.

Enhancing corporate brands through service robots: The impact of anthropomorphic design metaphors on corporate brand perceptions

AbstractThe increasing introduction of intelligent, interactive robots in the service industry raises concerns about the potential dehumanization of service provision and its influences on corporate brand perceptions. To avoid adverse effects, new service development (NSD) managers seemingly favor service robots that feature anthropomorphic design metaphors, so they appear more human‐like. The current research investigates explicitly how customers' perception of a robot's anthropomorphic design metaphors might spill over to affect corporate brand perceptions. Study 1, a picture‐based scenario study with 109 participants, reveals the impact of anthropomorphic design metaphors on untested corporate brand outcomes, such as brand trust and brand experience. Then Study 2, a video‐based scenario study with 530 participants, addresses whether these effects depend on the service context. In Study 3, a field study of 393 participants, the authors examine how anthropomorphic design metaphors influence other firm‐related outcomes (e.g., shopping enjoyment, sales). The combined results confirm that anthropomorphic design metaphors strongly affect brand trust and brand experience, as well as other critical firm‐related outcomes; they also reveal notable context effects, such that customers of people‐processing (e.g., care services) and mental‐stimulus‐processing (e.g., shopping assistance) services appear more likely to use anthropomorphic design metaphors as corporate brand cues. Our research encourages NSD managers and scholars to consider the effects of introducing anthropomorphic service robots on corporate brands.

Integrated visual transformer and flash attention for lip-to-speech generation GAN

Lip-to-Speech (LTS) generation is an emerging technology that is highly visible, widely supported, and rapidly evolving. LTS has a wide range of promising applications, including assisting speech impairment and improving speech interaction in virtual assistants and robots. However, the technique faces the following challenges: (1) Chinese lip-to-speech generation is poorly recognized. (2) The wide range of variation in lip-speaking is poorly aligned with lip movements. Addressing these challenges will contribute to advancing Lip-to-Speech (LTS) technology, enhancing the communication abilities, and improving the quality of life for individuals with disabilities. Currently, lip-to-speech generation techniques usually employ the GAN architecture but suffer from the following problems: The primary issue lies in the insufficient joint modeling of local and global lip movements, resulting in visual ambiguities and inadequate image representations. To solve these problems, we design Flash Attention GAN (FA-GAN) with the following features: (1) Vision and audio are separately coded, and lip motion is jointly modelled to improve speech recognition accuracy. (2) A multilevel Swin-transformer is introduced to improve image representation. (3) A hierarchical iterative generator is introduced to improve speech generation. (4) A flash attention mechanism is introduced to improve computational efficiency. Many experiments have indicated that FA-GAN can recognize Chinese and English datasets better than existing architectures, especially the recognition error rate of Chinese, which is only 43.19%, the lowest among the same type.

Service robot acceptance in museums: an empirical study using the service robot acceptance model (sRAM)

PurposeThis study aims to apply the service robot acceptance model (sRAM) to examine how attitude toward human–robot interaction (HRI) and engagement influence consumer acceptance of service robots in a frontline setting.Design/methodology/approachData was collected from 255 visitors who interacted with a robotic tour guide at a city museum. The data was analyzed using smart PLS 4.0.FindingsThe findings show the positive effects of subjective norms, appearance, perceived trust and positive emotion on both attitude toward HRI and engagement. In addition, social capability impacted attitude toward HRI, whereas perceived usefulness affected engagement.Practical implicationsTo deliver engaging museum experiences that bring about positive word-of-mouth and intention to visit, managers need to incorporate the sRAM dimensions in the design and deployment of service robots.Originality/valueThis research uses field data to empirically validate the sRAM in the context of service robot acceptance. It introduces engagement as a novel mediating variable, enriching current understanding of human-like qualities in HRIs.

Interaction Assessment of a Social-Care Robot in Day center Patients with Mild to Moderate Cognitive Impairment: A Pilot Study

As dementia-induced impairments of daily functioning escalate, novel cognitive stimulation techniques utilizing technological advances, like social robots, have surfaced. This study examines the interaction level of the EBO social-care robot with day center patients in Cáceres, Extremadura, Spain. The study uses systematic video analysis as a method of interaction assessment. This observational pilot study was performed on patients above 65 with mild to moderate cognitive impairment (Minimental State Examination ≥\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ge $$\\end{document} 21) receiving cognitive therapy at the AZTIDE social and health center. Two individualized 10–15 min sessions, replicating the Wizard of Oz technique, were conducted per participant, with the human operator’s commands being unnoticeably executed by the EBO robot. Of the six participants involved, all maintained complete eye contact with the robot, with 83.3%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} of the interactions recording maximum attention. Participants felt comfortable and calm, rating conversational factors such as attentiveness and naturalness as ’good’ or ‘excellent’. The high interaction level with the EBO robot suggests it as a promising tool for cognitive stimulation in patients with mild to moderate cognitive impairment. The systematic video evaluation also appears effective in assessing user–robot interaction, thus underscoring its potential utility in future social robotics research.

Babypapa: Multiple Communication Robots to Enrich Relationship Between Parents and Child–Design and Evaluation of KANSEI Model to Control Closeness—

There is a need to create a well-being oriented society to improve people’s lives by enhancing their mental satisfaction. In this study, we examined the changes in human emotions based on human–robot interaction by using a communication robot called babypapa. We defined KANSEI as the sensitivity of emotional change to the robot’s behavior and established a KANSEI model. Specifically, to clarify the behavior that the robot should exhibit to make children feel close to it, we conducted play experiments between the robot and 3–4 year-old children to investigate the relationship between the robot’s behavior and the feeling of closeness. The results of the experiment showed that contact and noncontact behaviors of the robot contributed to the feeling of closeness. We demonstrated a certain tendency of closeness and robot behavior.

From CySkin to ProxySKIN: Design, Implementation and Testing of a Multi-Modal Robotic Skin for Human-Robot Interaction.

The Industry 5.0 paradigm has a human-centered vision of the industrial scenario and foresees a close collaboration between humans and robots. Industrial manufacturing environments must be easily adaptable to different task requirements, possibly taking into account the ergonomics and production line flexibility. Therefore, external sensing infrastructures such as cameras and motion capture systems may not be sufficient or suitable as they limit the shop floor reconfigurability and increase setup costs. In this paper, we present the technological advancements leading to the realization of ProxySKIN, a skin-like sensory system based on networks of distributed proximity sensors and tactile sensors. This technology is designed to cover large areas of the robot body and to provide a comprehensive perception of the surrounding space. ProxySKIN architecture is built on top of CySkin, a flexible artificial skin conceived to provide robots with the sense of touch, and arrays of Time-of-Flight (ToF) sensors. We provide a characterization of the arrays of proximity sensors and we motivate the design choices that lead to ProxySKIN, analyzing the effects of light interference on a ToF, due to the activity of other sensing devices. The obtained results show that a large number of proximity sensors can be embedded in our distributed sensing architecture and incorporated onto the body of a robotic platform, opening new scenarios for complex applications.

Sonic Sleight of Hand: Sound Induces Illusory Distortions in the Perception and Prediction of Robot Action

AbstractFor efficient human–robot interaction, human operators need to be able to efficiently represent the robot’s movements in space and predict its next steps. However, according to frameworks of Bayesian multisensory integration, features outside the motion itself—like the sounds a robot makes while it moves—should affect how otherwise identical motions are perceived. Here, we translate an established psychophysical task from experimental psychology to a human–robot interaction context, which can measure these distortions to motion perception. In two series of preregistered studies, participants watched a humanoid robot make forward and backward reaching movements. When the robot hand suddenly disappeared, they reported its last seen location, either with the mouse cursor (Experiment 1a and 1b) or by matching it to probe stimuli in different locations (Experiment 2a and 2b). The results revealed that even small changes to the robot’s sound robustly affect participants’ visuospatial representation of its motions, so that the motion appeared to extend further in space when accompanied by slightly (100 ms) longer sounds compared to slightly shorter sounds (100 ms shorter). Moreover, these sound changes do not only affect where people currently locate the robot’s motion, but where they anticipate its future steps. These findings show that sound design is an effective medium for manipulating how people represent otherwise identical robot actions and coordinate its interactions with it. The study acts as proof of concept that psychophysical tasks provide a promising tool to measure how design parameters influence the perception and prediction of robot motion.

Design and control of a novel variable stiffness actuator based on antagonistic variable radius principle

Variable stiffness actuators (VSAs) are essential for ensuring safe human–robot interactions in robotic applications. This paper proposes a novel rotary VSA using an antagonistic Hoberman linkage mechanism (AHLM), which offers a large stiffness range and a compact structure. The VSA-AHLM consists of two sets of antagonistic-type quadratic springs based on spiral cams connected to the Hoberman linkage mechanism (HLM) through four cables. By simultaneously adjusting both the radius of the HLM and the spring preload, the stiffness of the VSA-AHLM can be varied within a large range. Furthermore, the position and stiffness of the VSA-AHLM can be controlled independently by two rotary motors. The geometric parameters of the spiral cam are determined to achieve the desired linear stiffness–elongation behavior of a quadratic spring, and detailed models of the actuator’s stiffness, elastic energy, and torque are established. An actuator prototype is fabricated to demonstrate the proposed variable stiffness approach. Experiments show that the developed actuator can achieve significant stiffness changes and exhibits excellent positioning and trajectory tracking performance.

Decentralized variable impedance control of modular robot manipulators with physical human–robot interaction using Gaussian process-based motion intention estimation

Decentralized variable impedance control of modular robot manipulators with physical human–robot interaction using Gaussian process-based motion intention estimation