搜索结果：Frontiers in robotics and AI

Human-AI teaming is increasingly being studied in applied and high-stakes settings, yet the evidence remains dispersed across domains, constructs, and research traditions. This fragmentation also limits efforts to connect broader human-AI findings to human-robot teaming (HRT), where embodied systems make issues such as coordination, autonomy management, communication, and safety more immediate in real-world interaction. To provide a clearer picture of the field, we conducted a PRISMA-guided systematic review with bibliometric analysis of 104 peer-reviewed empirical studies published between 2015 and 2025 and identified through Engineering Village, IEEE Xplore, PubMed, ScienceDirect, and Web of Science. The review maps where human-AI teaming has been evaluated and what teaming aspects are most frequently examined. Cross-domain and interdisciplinary studies were the largest category, representing broad workplace or team-based investigations not tied to a single industry and instead focused on general collaboration issues such as communication, teamwork, coordination, and coworker interaction. Gaming and entertainment, aviation, military and defense operations, emergency response and public safety, and healthcare also represented substantial portions of the literature. Across studies, performance was the most frequently examined aspect, followed by trust, explainability and transparency, decision-making, and team processes. Bibliometric patterns suggest a shift since 2020 from foundational demonstrations in controlled settings toward applied, higher-stakes contexts where trust dynamics, communication, and ethical accountability more directly shape adoption and sustained performance. Evidence points to a practical conclusion that human-AI teaming works best when the interaction supports coordination, allowing users to form accurate expectations of the AI, adjust autonomy and delegation across task phases, and use transparency cues that calibrate reliance without adding burden. For HRT, these findings reinforce the importance of shared control, mixed-initiative interaction, and designs that help humans and robots coordinate action over time rather than simply divide functions. We conclude by outlining implications for designing and evaluating human-AI teams as socio-technical systems and for prioritizing longitudinal and in-context studies that capture how teaming evolves over time.

Skin-to-skin tactile stimulation plays a critical role in the neurodevelopment of preterm infants, contributing to improved physiological stability, sensory integration, and caregiver bonding. However, the delivery of consistent tactile therapy in neonatal intensive care units is often limited by the availability of trained personnel and the inherent variability of manual application. This creates a need for assistive technologies capable of reproducing clinically relevant tactile stimuli in a controlled and repeatable manner. This work presents a soft pneumatic robotic system designed to replicate clinically inspired tactile stimulation for neonatal therapy. The proposed approach integrates experimental characterization of manual tactile interactions, pneumatic system modeling, and closed-loop control. Force measurements obtained from a neonatology specialist were used to define clinically grounded stimulation levels, with mean values of 0.594 N for light stimulation and 1.267 N for moderate stimulation. These values were mapped to actuator pressure through experimentally identified linear relationships between force, pressure, and electrical current, enabling the definition of therapeutic pressure references. A 3 × 3 matrix of textile pneumatic actuators was integrated with an electro-pneumatic actuation system, pressure sensing, and current monitoring to implement the proposed therapy platform. Two control strategies were evaluated: a baseline pressure deadband controller and a refined deadband controller incorporating actuation tuning and current-based protection. Experimental results demonstrated that the refined controller increased the time within the therapeutic pressure band from 30.8% to 76.1%, while reducing mean pressure error from 0.68 kPa to 0.15 kPa and RMS error from 0.92 kPa to 0.38 kPa. Robustness tests under varying mechanical interface conditions showed stable and consistent pressure regulation performance. These results demonstrate the feasibility of translating clinically derived tactile stimulation into controlled pneumatic actuation using a soft robotic platform. By combining clinically grounded references, pressure-based closed-loop control, and safety-oriented current monitoring, the proposed system provides a reproducible and safe preclinical platform for neonatal tactile therapy and supports the development of assistive soft robotic technologies for clinically representative neonatal care environments.

Artificial intelligence is increasingly capable of expressing empathy through language, yet the integration of physical touch-an important cue for social connection-remains fragmented. Although robots utilise language or touch individually, few systems coordinate both modalities, potentially limiting their capacity for affective human-robot interaction (HRI). This scoping review maps social robots that combine spoken language and tactile interaction (e.g., hugging, stroking, warmth, vibration), examines how these modalities are coordinated in existing systems, and synthesises reported user outcomes and design implications. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) guidelines, searches across five databases (IEEE Xplore, PubMed, ACM, Web of Science, Scopus) and supplementary web sources identified 11 distinct HRI implementations that pair speech with active or invited touch. Of these, eight implementations included explicit comparison conditions (e.g., speech-only vs. speech + touch, or touch-only vs. touch + speech), enabling assessment of the added value of combining modalities. Across comparative studies, combining speech and touch showed potential to be more effective than speech-only or touch-only HRI in some contexts. This integration can make robots appear more caring, empathic, and human-like, while strengthening attachment, increasing willingness to self-disclose, and helping users feel calmer (e.g., lower heart rate). However, outcomes were implementation-dependent, with some studies reporting no additional benefit from the combined modalities. Across the evidence base, the review found a consistent suggestive pattern that warm (e.g., near skin temperature), soft, naturalistic touch tends to support more positive affective HRI outcomes than cold, rigid, "mechanical" touch. The evidence base was also largely dominated by short, lab-based studies using existing, typically rigid robotic platforms not purpose-built for affective speech-touch interaction. Speech-touch integration in social HRI is a small but promising area, particularly for healthcare and emotional-support applications (e.g., supporting children in hospital). Despite this potential, very few robots are purpose-built for coordinated speech and touch. Affective speech-touch HRI remains challenging because of its psychological, socio-cultural, and engineering demands. Progress will likely require soft, safe, warm, and increasingly autonomous systems that move beyond repurposed rigid platforms. https://doi.org/10.17605/OSF.IO/2PA6J, identifier OSF.IO/2PA6J.

The use of social robots in education has increasingly focused on how different role framings, such as tutor, peer, or novice, shape children's engagement and learning. However, most studies employ a single robot whose role is manipulated behaviourally (e.g., the same robot is used to act either as a peer or as a tutor), leaving open the question of how children respond when multiple, physically distinct robots adopt complementary roles within the same session. In this exploratory feasibility study, we introduce a blue multi-robot learning environment in which one robot acts as a tutor and the other as a novice peer. The robots supported an early word-learning task in which children learned novel object names and were later asked to name or identify them. In the proposed scenario, participants were exposed to novel words assigned to unusual or unconventional objects (e.g., dog toys and shapes made with interlocking disks), alongside familiar objects. After an initial training phase, children were asked to locate or name the novel items. Sixteen children aged 4-5 years interacted with both robots while their attention, affect, and engagement behaviours were recorded. The study characterised children's distribution of attention during a word-learning task involving a tutor and a novice peer robot, including attention to task-relevant objects and robots and its relation to attentional complexity, affect, and engagement, as well as the relation between individual characteristics (language ability, age, and media exposure) and task performance, measured as correct naming or pointing during recall. Children consistently attended to task-relevant objects throughout the session, with attention distributed across objects and robots in structured patterns. Attentional complexity co-occurred with sustained engagement and positive affect. Task performance and engagement showed little variation with age or media exposure, while baseline language ability was negatively associated with recall performance. Overall, the findings indicate that a multi-robot learning configuration is feasible and capable of supporting sustained engagement and structured attentional behaviour in young children. While the results are exploratory and limited by sample size, they provide initial evidence that complementary robot roles can be meaningfully integrated within early learning activities and motivate further systematic investigation.

Despite strong evidence that repetitive home-based rehabilitation improves functional recovery after stroke, current delivery models still show gaps in continuity of care and patient engagement. AI-driven Embodied Conversational Agents (ECAs) could provide personalized home support through natural-language guidance on prescribed exercises, reinforcement of neuroplasticity, clarification of therapeutic principles, and motivational support. However, clinical deployment remains challenging. Many robotic platforms lack real-time interaction capabilities such as speech processing, gesture execution, and attention tracking, while Large Language Models (LLMs) may produce factual errors or inconsistent responses. Early development is also constrained by limited access to real users due to practical and ethical considerations. To address these challenges, we propose a Design-Based Research methodology for human-AI co-design and evaluation of ECAs (co-AI DBR), where generative AI facilitates iterative cycles of design, testing, and refinement. Co-AI DBR combines synthetic patient generation with real-code execution to simulate, emulate, and evaluate the ECA platform and its LLM-based conversational pipeline. To validate the method in a post-stroke rehabilitation context, a virtual ECA was first tested with synthetic patients to assess technical implementation and accuracy of LLM responses. A pilot deployment using the Furhat robot as an ECA was then conducted with patient relatives and rehabilitation professionals to evaluate the voice interface and augmented communication. LLM responses to questions from real participants showed higher lexical diversity (MTLD ≈ 134 vs. 93.9) and lower repetition (Yule's K ≈ 66.8 vs. 115.4) than responses to synthetically generated questions. Responses remained factually consistent, with no contradictions and complete gender invariance, although slightly lower hapax rates were observed (88.8% vs. 99.4%). Usability scores were higher among relatives (M = 86.67) than professionals (M = 72.50), while Intrinsic Motivation Inventory scores indicated similarly high motivation in both groups (M = 6.32 vs. 6.12). The results suggest that co-AI DBR can support early design and evaluation of ECAs when direct patient testing is limited. By combining synthetic patient generation with real-code execution, generative AI supports iterative knowledge building during the prototyping and refinement of LLM-based ECAs. This methodology enables the practical development of ECA to support home-based post-stroke rehabilitation.

Gait analysis is essential in clinical evaluation, biomechanics, and rehabilitation, yet conventional approaches often rely on complex marker-based systems that limit accessibility and real-time feedback. The SANE (eaSy gAit aNalysis systEm) platform was launched in 2020 and has previously been evaluated in multi-subject laboratory and clinical studies, where it demonstrated agreement with gold-standard marker-based systems for core spatiotemporal parameters and achieved high test-retest, inter-rater, and intra-rater reliability. Building on this validated foundation, the present work provides a system characterisation and robustness analysis of the latest dual-depth, real-time SANE implementation. The updated SANE system enables real-time extraction and visualisation of an expanded set of spatiotemporal and angular gait parameters-including gait speed, step and stride length, cadence, step and stride time, step width, foot angles, double support, and gait phase durations-using two depth cameras and AI-based pose estimation. A total of 80 walking trials performed by a healthy adult (39 years, 1.74 m, 73.0 kg) were acquired across four sessions over 1 week, with complete system shutdown and restart between sessions to rigorously challenge operational stability. Session-level means, within-session standard deviations, and Relative Error Measurement (REM%) between sessions were used to quantify robustness and session-to-session variability. Across all four sessions, gait outputs remained within published normative ranges for healthy adults. REM% values for primary spatiotemporal parameters were consistently below or around 5%, and standard deviations were low and comparable to values reported for marker-based systems, indicating stable, repeatable measurements over repeated restarts and days. Real-time computation and visualisation at frame rates up to approximately 80 frames per second further distinguish this system from traditional post hoc workflows. These findings characterise the operational robustness and real-time capabilities of the dual-depth SANE system in a controlled, single-participant setting and support its use as a practical, marker-less gait assessment tool in clinical and research environments, while motivating future studies on larger and pathological cohorts.

Human-machine teaming allows people to leverage the impressive capabilities of autonomous robotic teammates to safely accomplish challenging tasks. Although users may be experts in their fields, robotic interfaces need to be intuitive to the general population and able to quickly interpret minimal user input from multiple modalities in directing autonomous teammates toward key locations for information-based tasking. This work presents a flexible multimodal algorithmic and visual interface that enables dynamic reprogramming of autonomous planning algorithms, focusing on the use of uncrewed aerial systems engaged in outdoor search and rescue. The Responsive Interface for iNtuitive Aircraft Operation (RINAO) leverages known geographic database information, such as trail networks, in conjunction with a variable set of user-defined features, such as search areas and landmarks, to efficiently infer a mission-specific, uncertainty-aware geospatial interest distribution that informs optimal planning algorithms through reward shaping. The approach is validated using 10 experts in public safety with 13.5 years of median operational experience. Results of this user evaluation show that the system enables effective and efficient alignment of geospatial interest and above-average usability. Evaluating the system's performance against an inverse reinforcement learning (IRL) baseline, we find that our approach meets or exceeds the baseline's value alignment while performing inference in substantially less time and with less user input. These results demonstrate that multimodal preference inference can enable rapid and intuitive mission specification for human-robot teams operating in time-critical environments.

The digital transformation of hospitality is increasingly driven by technologies that integrate human and operational elements of service work. Within this evolution, human-centered Digital Twins leverage both human-related and operational data to digitally represent employees within their work contexts, enabling real-time feedback and data-informed decision making for both employees and organizations. Despite their potential, little is known about how hospitality employees perceive these systems or what shapes their willingness to use them. This study examines the individual perceptual factors that influence employees' intention to use a human-centered Digital Twin, focusing on performance expectancy, effort expectancy, and trust in the system. In addition, the study explores the role of gamification as a system design feature that may shape how these perceptions translate into adoption intentions. Data were collected from 141 customer-facing hotel employees across Europe using a structured survey based on validated scales. An Exploratory Factor Analysis confirmed the reliability and structural validity of the measurement model, and multiple linear regression analysis was used to test both the baseline and the extended models. Results show that all three perceptual factors significantly and positively influence intention to use, with performance expectancy emerging as the strongest predictor. Gamification moderates the relationship between effort expectancy and intention to use in a non-reinforcing manner: when gamification is higher, the positive effect of effort expectancy becomes weaker. These findings suggest that interaction design can alter how employees experience the ease of using advanced digital systems. This study provides empirical evidence on the perceptual determinants that influence front-line employees' intention to use a human-centered Digital Twin in hospitality settings, highlighting the role of both core adoption beliefs and system design features in shaping adoption intentions.

Densely populated enclosed environments, characterized by complex thermal stratification and overlapping breathing zones, represent high-risk clusters for the airborne transmission of respiratory pathogens. To address the dual challenges of physical boundary fidelity and prohibitive computational latency in traditional solvers, this study proposes a physics-validated, data-driven framework for the rapid spatiotemporal prediction of sneeze-induced pollutant dispersion. A CFD-Robotics Twin system was developed, utilizing an anthropomorphic manipulator governed by a Transformer-based Imitation Learning policy to replicate non-linear human sneezing kinematics. To ensure rigorous physical fidelity, the simulated flow fields and particle trajectories were validated through a dual-stage experimental benchmark involving anemometer measurements and robotic-arm-nozzle discharge tests. On this basis, a spatial-preserving U-ConvLSTM architecture was developed. By integrating a convolutional U-Net encoder with ConvLSTM layers and symmetric skip-connections, the model maintains absolute physical coordinates (x,y) and bypasses the topological destruction inherent in conventional flattened architectures. Evaluation via mass error ( ε mass ) and Center of Mass distance confirms strict adherence to Eulerian conservation laws. Results demonstrate that the surrogate model achieves a computational acceleration of three orders of magnitude while maintaining high structural similarity (Structural Similarity Index Measure = 0.992). Furthermore, the framework translates abstract concentration fields into practical engineering metrics, including the Dynamic Safety Radius and vertical exposure windows. This research provides a scientifically rigorous tool for real-time risk assessment and the optimization of indoor spatial layouts to mitigate pathogen exposure.

This article explores the self-efficacy of guide robot (GR) users and assesses the value of integrating GRs into organizational workflows. The study consisted of two stages, both conducted in Estonia. First, we carried out a preliminary quantitative pilot study by applying the newly developed Guide Robot User Self-Efficacy Scale (GRUSES) in controlled and uncontrolled organizational settings. This pilot stage examined users' confidence in using GRs across demographic variables, prior robot experience, and interaction contexts, and generated initial insights for the qualitative stage. In the main stage, we conducted semi-structured interviews with three stakeholder groups: GR end users, organizational administrators, and GR distributors. The preliminary survey indicated that prior robot experience was associated with higher self-efficacy, whereas age and gender differences were not statistically significant in this sample. Users' self-efficacy was lower in uncontrolled real-life use than in controlled guided scenarios, although this difference should be interpreted cautiously because the groups were not randomly assigned. The qualitative interviews, which form the core of the study, identified technical, user-related, and organizational barriers to integrating GRs into everyday workflows. Based on these findings, we propose an exploratory three-actor framework linking robot capability, user readiness, and organizational readiness. The article also provides recommendations for guide-robot deployment in service organizations. As the GRUSES instrument remains under development, the survey results are interpreted as exploratory and hypothesis-generating.

The pervasive integration of robots into daily life necessitates advanced human-robot interaction (HRI) capabilities, particularly the accurate understanding of human physiological and cognitive states. The current state of the widely used Robot Operating System (ROS2) lacks standardized mechanisms for representing and communicating human states. This paper introduces ROS 4 Healthcare (ROS4HC), a comprehensive open-source framework designed to standardize the acquisition, representation, and integration of human sensing data into robotic systems. ROS4HC provides unified message types, modular sensor drivers, signal processing libraries, and visualization tools for physiological, biological, and physical signals. This framework is validated through empirical case studies in healthcare robotics, including a heart rate (HR)-adaptive wheelchair velocity modulation, an autonomous treadmill system integrating physiological feedback, and a nocturnal monitoring system based on a robotic rocking bed. These case studies demonstrate that the framework enables modular component reuse, standardized communication, and interoperability for better human-robot integration. Beyond healthcare, we highlight ROS4HC's generalizability for critical applications such as industrial safety, human-robot collaboration, and performance monitoring, establishing a standardized infrastructure for safer, more adaptive, and context-aware robotic systems across diverse domains.

Foundation models, in particular large language models (LLMs), are finding increasing popularity when used in describing goals for robotic control, decision making, and execution. Recently, proposals for hybrid paradigms leveraging strengths of reinforcement learning (RL) agents in tandem with LLMs for robotic control have been demonstrated. The interface between the RL agents and the language model however offers a unique opportunity to explore how prompt framing may affect such hybrid systems. This work presents a controlled experimental platform to measure and better understand how manipulation of the interface between RL agents and an LLM impacts behaviour of a hybrid advisor-arbiter architecture. We compared three agents under matched evaluation protocols and initializations in a simulated navigation environment: (i) RL-only tabular Q-learning; (ii) LLM-only (stateless) action selection; and (iii) a hybrid LLM + RL agent. Under a constrained interaction budget (10 episodes per world), the hybrid LLM + RL agent achieves higher mean success and higher mean cumulative reward than both RL-only and LLM-only baselines. Advisor-channel ablations (random recommendations and null recommendations) reduce performance, indicating that structured advice contributes beyond adding extra text. We further demonstrate prompt framing as a controlled factor by evaluating navigation-role personas, narrative personas, and relational variants of a caregiver prompt under matched conditions, yielding heterogeneous effects across framings. The contribution of this work is to provide a structured testbed and evaluation approach for investigating the impact of prompt framing on multi-step decision making and control tasks.

Actuated universal joints are used in a wide range of robotic applications, including mobile snake robots, snake-arm robots and robotic tails. They are employed in applications such as search and rescue and confined space inspection. These can use remote cables, fluid driven systems, or inline motors. To realise the benefits of inline actuation while keeping the system compact with a high power to weight ratio, an actuated universal joint (AUJ) was developed using an ''antagonistic triad'' of three twisted string actuators in our previous work. However, the design had numerous drawbacks in its prototype form, namely, a limited angle range, poor accuracy due to the angular feedback sensors used, and issues with string failure due to mechanical design choices. In this publication, we performed a root-cause analysis of these issues, and partially or fully mitigated some of them by reducing the distance between the twisted string actuator (TSA), removing geometry which caused premature string failure, and exchanging the angular feedback sensors for more accurate ones. As a result, angle range was increased from ± 14.5° to ± 26° for a single axis, and ± 6° to ± 20° for a dual axis movement. Angular feedback sensor accuracy increased from ± 0.21° to ± 0.11°, and no string failures occurred within load limits. The performance of the mechanism was further characterised with additional experiments for increased follower load and angular velocity. A novel method to adjust the transmission ratio during operation (active transmission adjustment) was proposed and simulated, and its advantages over existing mechanisms for a snake robot in a multi-segment configuration were theoretically evaluated.

Convincing learners to engage deeply with complex moral and philosophical concepts remains a major challenge in contemporary learning environments, particularly within increasingly digital educational settings. Although conversational AI offers new possibilities for interactive learning, its potential for supporting ethics education remains underexplored. This study examines the effectiveness of a chatbot-based learning condition compared with a reading condition and a no-intervention control group. Learners' outcomes were assessed through cognitive tests, self-reported emotional engagement, heart rate variability, and electroencephalographic (EEG) activity. Results showed that both the chatbot and reading conditions improved moral understanding relative to the control group. Emotional engagement was assessed during the chatbot interaction and indicated strong affective involvement among participants. EEG measures suggested increased neural engagement during the instructional conditions, while the reading condition demonstrated higher indices of attentional focus. Both intervention conditions also showed greater physiological engagement than the control group. These findings suggest that conversational AI can serve as a promising interactive tool for supporting moral learning and for facilitating deeper engagement with abstract ethical concepts in contemporary educational contexts.

Socially aware robot navigation requires robots to move among people in ways that respect human social norms, comfort, and perceived safety. Proxemics, the regulation of interpersonal space, plays a central role in this process. Applied HRI work often relies on simplified, static representations of personal space, overlooking the dynamic, asymmetric, and context-dependent nature of proxemic behavior observed in real-world interactions. The literature reflects a clear progression from simplified, concentric representations of proxemics toward increasingly context-sensitive and interaction-dependent models. This evolution indicates a growing consensus that interpersonal comfort cannot be adequately captured by a single, universal geometric shape. Instead, proxemic representations vary as a function of interaction context, task demands, cultural norms, and environmental constraints. To build on this evolution, we propose a comprehensive taxonomy of proxemics for socially aware robot navigation addressing gaps in the literature. Grounded in an extensive review of proxemics-related HRI studies published between 2020 and 2025, the taxonomy was developed through a hybrid methodology that integrates a top-down analysis of established HRI taxonomies and an AI exploratory approach with a bottom-up extraction of variables from 39 empirical studies. The resulting taxonomy systematically organizes proxemic dimensions into four interrelated clusters: Human, Robot, Environment, and Context. Together, these clusters capture the key variables shaping proxemic form (shape geometry and the scale of the personal zone boundary) and dynamics, including human activity and posture, robot design and behavior, environmental structure, task context, and the dynamic spatial properties of proxemics as captured by their metrics (the proxemics output variables). The proposed structured taxonomy of proxemics will inform the design of socially adaptive robot navigation systems and provide a foundation for future empirical research. Our analyses reveal significant gaps in current research practices, including limited consideration of interactions among multiple variables, overreliance on static laboratory settings, and insufficient integration of contextual and human-centered variables. To address these limitations, we propose future directions.

Bilateral teleoperation enables intuitive interaction with remote environments and is widely used in surgery, space, and industry. However, educational tools often rely on costly hardware or purely virtual setups, limiting accessibility and reducing opportunities for hands-on learning. This paper presents the Telekit, a low-cost bilateral teleoperation system designed to support practical education. The Telekit is built on Stanford's open-source Hapkit and features a gear-based transmission for improved robustness, along with a force-sensitive resistor at the handle for rendering real-world interactions. Communication and control are implemented using MATLAB, achieving a measured single-byte round-trip delay of 2 ms. Two control strategies, Position-Position (PP) and Position-Force (PF), were developed and tested in both virtual and physical environments. PP control incorporates damping and friction compensation, while PF control utilizes force feedback from the integrated sensor. For PP control at low frequency (0.24 Hz), damping combined with friction compensation resulted in a mean communication delay of 230 ms and a mean tracking error of 3.4 ° between leader and follower units. At higher frequency (1.15 Hz), damping alone reduced the mean communication delay to 140 ms but increased the mean tracking error to 8.7 ° . PF control enabled users to perceive different stiffness levels, with soft, medium, and hard stiffness measured at 0.17 N/ ° , 0.41 N/ ° , and 0.68 N/ ° , respectively. The Telekit demonstrates that a low-cost platform can effectively support both position tracking and stiffness perception. Although performance varies with operating frequency, the system provides meaningful haptic feedback and reliable functionality. As such, it offers an accessible, hands-on solution that bridges theoretical concepts and practical experimentation in teleoperation education.

While shared activities foster connection between people living with dementia (PLWD) and their care partners, emotional distress and daily caregiving responsibilities often make them difficult to initiate. This paper investigates the adaptation of a socially assistive robot, Ommie, to guide shared deep breathing and singing activities for these pairs. We refined the robot's behaviors through two interaction design sessions with people living with dementia and care partners, mediated by an occupational therapist. In a subsequent study with 17 pairs, participants engaged in deep breathing and singing activities with the robot as well as in-session semi-structured interviews, and we conducted post-hoc video analysis to explore their interactional dynamics. Participants reported the interactions as easy to follow, calming, and familiar. Post-hoc video analysis revealed patterns of intimacy and synchrony, including frequent physical touch, mutual gaze, and rhythmic coordination. We also observed instances of personal memory recall and a playful atmosphere, in which pairs often used humor as a coping mechanism after deviations from the robot's instructions. From our observations, we discuss three design opportunity spaces: the robot as the focus for synchronization, as an instrument of joint play, and as a source of familiarity versus variety.

As soft robots become more prevalent in society, it becomes increasingly important to understand how laypersons evaluate their risks and benefits relative to conventional rigid robots. This article investigates public perceptions of soft versus rigid embodiments of socially assistive robots (SAR) and rescue robots (RR) and explores how these perceptions can inform early-stage robot design. We conducted an online study, using a scenario-based intervention design combined with Cognitive-Affective Maps (CAMs) to capture participants' cognitive-emotional belief structures. In a first step, participants constructed CAMs depicting perceived risks and benefits of rigid SAR or RR. After reading a second scenario introducing the corresponding soft robot, they revised their maps, allowing a direct contrastive comparison between the first (rigid) and second (soft) scenario. Quantitative analyses showed that, across both application domains, post-intervention evaluations (after the soft-robot scenarios) were more positive than pre-intervention evaluations of rigid robots. Qualitative analyses revealed distinct argument structures: After learning about soft robots, participants added concepts emphasizing safety, emotional comfort, and adaptability, but also introduced concerns such as fragility and emotional dependence, whereas rigid robots were linked to precision, robustness, and efficiency, alongside worries about technical failure, data security, and emotional detachment. By integrating intervention-based CAMs with data-driven qualitative synthesis, the study demonstrates a scalable method for early public engagement that uncovers how laypersons qualitatively negotiate trade-offs between soft and rigid designs in plausible early-stage scenarios. These insights provide actionable input for human-centered design of soft robots, supporting responsible and socially aligned robot development.

Embodied therapies such as movement therapy have shown promise in enhancing emotional regulation, cognitive engagement, and physical rehabilitation. However, scalable and personalized delivery of such interventions remains a critical challenge. This work presents SIVAM (Synergy-based Intuitive Virtual and Augmented Mental Health platform), a multimodal system that integrates immersive virtual environments, markerless motion capture, physiological sensing, and humanoid robotic mirroring to support affect-aware interventions for mental health. SIVAM combines RGB camera-based skeletal tracking with EEG, EMG, ECG, GSR, and skin temperature sensing using a wearable dry electrode headset to create a closed-loop therapeutic framework. Movement synergies-low-dimensional coordinated patterns across body joints and muscles-are extracted from motion data and aligned with physiological signals to infer affective and motor states in real time, serving as potential biomarkers of stress. The system further introduces a plane-wise movement model that enables natural 3D avatar navigation using a single RGB camera, enhancing embodiment and interaction with virtual environments. A pilot study (N = 5) with five participants of varying dance experience demonstrated reliable motion tracking, real-time synchronization of physiological and movement data, and robust avatar and robot mirroring across diverse movements. These results highlight the feasibility of combining multimodal sensing, virtual avatars, and socially assistive robots to enable scalable, home-based movement therapy.