Search Results (356)

Digital-twin-enabled human–machine collaboration (HMC) has increasingly been proposed as a system-level approach for connecting human operators, robots, sensors, artificial intelligence modules, and manufacturing resources. However, the literature varies substantially in what is called a digital twin, how physical and virtual models are coupled, whether models are updated from physical data, and how far systems have progressed beyond simulation or controlled laboratory demonstrations. This structured integrative review examines the conditions under which a digital twin can function as an integration layer for HMC in sustainable smart manufacturing, rather than assuming that such integration is already established industrial practice. The literature corpus was assembled through searches of the Web of Science Core Collection, Scopus, and IEEE Xplore, complemented by Google Scholar-based citation tracking and backward and forward citation tracing. The core search focused on studies published from 1 January 2020 to 5 August 2026, while earlier seminal studies were retained to support definitions and historical context. Studies were screened using explicit criteria for manufacturing relevance, physical–virtual coupling, state synchronization or model updating, feedback capability, and validation setting, and were critically coded by model type, integration mechanism, deployment maturity, and sustainability evidence. The review compares multimodal perception and human-state modeling, intention understanding and augmented interaction, task allocation and shared planning, digital-twin architectures, adaptive control and safety verification, and human–AI decision-making. The evidence indicates that digital twins are promising as coordination and verification layers, but many reported systems remain conceptual, simulation-based, or limited to controlled physical prototypes. Key barriers include model fidelity, online model updating, real-time synchronization, cross-platform interoperability, safety assurance, human-data governance, and the limited availability of directly measured sustainability outcomes. Future work should prioritize validated hybrid models, traceable model-update mechanisms, staged virtual-to-physical deployment, interoperable data contracts, and longitudinal evaluation of technical, human, economic, and environmental performance. Full article

Co-Creative Robotics combines computational creativity, robotic embodiment, and human–robot collaboration to support or generate creative behavior in physical and social environments. As these systems become more autonomous, data-intensive, and interactive, cybersecurity and privacy can no longer be treated as external safeguards added after creative functionality has been designed. This PRISMA-informed review investigates whether principles of cybersecurity-by-design and privacy-by-design can be integrated into Co-Creative Robotics without constraining creativity, autonomy, and user agency. The database search covered ACM Digital Library, Google Scholar, IEEE Xplore, Scopus, SpringerLink, and Web of Science, and was complemented by two focused backward and forward snowballing iterations. From 623 database records, the final synthesis includes 27 primary studies. The results show that direct literature combining cybersecurity, privacy, and Co-Creative Robotics remains limited, but evidence from creative HRI, social-robot privacy, cyber-physical security, privacy-preserving interaction design, security modeling, and robot ethics supports a conditional answer. Integration is feasible when security and privacy mechanisms are adaptive, explainable, participatory, context-sensitive, and lifecycle-aware. However, the evidence on transparency-oriented privacy mechanisms is mixed: improvements in awareness or acceptance do not consistently translate into reduced disclosure or greater perceived safety. Rigid controls may constrain creative exploration, whereas well-designed controls can support trust, accountable autonomy, safe embodiment, privacy-aware interaction, provenance, and agency-preserving creativity. The review proposes a conceptual lifecycle-oriented research agenda for secure and privacy-aware Co-Creative Robotics. Full article

Large language models (LLMs) are expanding the capabilities of socially assistive robots (SARs) through natural dialogue, personalisation, multimodal reasoning, retained interaction context, and adaptive behaviour in healthcare. Integrating generative language models into robots, however, complicates evaluation because fluent output may exaggerate perceived competence and increase the risks of hallucination, overtrust, privacy exposure, relationship dependency, and unsafe reliance on advice or actions. This PRISMA-informed review synthesises healthcare robotics, human–robot interaction, LLM-enabled systems, ethics, implementation, and care delivery. Database searches returned 128 records, of which 110 were unique after deduplication. Supplementary retrieval and assessment yielded 85 substantive sources spanning background mapping, primary analysis, and governance. Studies focused mainly on feasibility, usability, acceptability, dialogue quality, and short-term engagement, whereas longitudinal safety, governance of retained interaction context, comparative effectiveness, workflow integration, and sustained healthcare value received limited attention. These gaps indicate that evaluation of LLM-enabled SARs must account for physical presence, social role, interaction memory, and potential actions rather than focus on conversational performance alone. The review therefore proposes HEART, a healthcare-specific evaluative architecture comprising Human-Centred Communication, Ethical and Trustworthy Deployment, Adaptive and Embodied Intelligence, Relationship Continuity, and Translational Healthcare Value. HEART uses boundary rules, operational indicators, qualitative labels, and non-additive deployment gates to separate evaluative domains, define assessable outcomes, summarise reported support, and prevent strengths in one area from masking critical safety or governance failures. Future research should validate HEART through longitudinal and comparative assessment of hallucination severity, language-to-action safety, long-term effects, equity, and post-deployment monitoring. Full article

The growth of single-person older adult households has heightened concerns about social isolation, chronic disease management, and diminished quality of life (QoL). A systematic review with meta-analysis was conducted to examine the efficacy of human-centered AI healthcare interventions on QoL among older adults living alone. Five electronic databases (PubMed, Web of Science, CINAHL, Embase, and Cochrane CENTRAL) were searched (January 2020–March 2026) following PRISMA 2020 guidelines. Only randomized controlled trials (RCTs) were eligible. Methodological quality was appraised with the Cochrane RoB 2 tool; pooled effect estimates were derived via random-effects modeling. Fourteen RCTs (N = 2840) were included. Intervention types comprised conversational agents, socially assistive robots, remote monitoring systems, integrated platforms, and AI-driven mHealth applications. Meta-analysis demonstrated significant improvements in overall QoL (SMD = 0.40, 95% CI: 0.27–0.52, I² = 59%), depression (SMD = −0.35, 95% CI: −0.43 to −0.26), and social connectedness (SMD = 0.38, 95% CI: 0.26–0.51). Subgroup analyses showed stronger effects for interventions with personalized feedback and human interaction. GRADE certainty was moderate for all three primary outcomes. GRADE certainty for secondary outcomes was moderate for physical health but low for self-management and cognitive function. Human-centered AI healthcare interventions significantly improve QoL and psychosocial outcomes among older adults living alone. Future research should prioritize long-term effectiveness, ethical implementation, digital inclusion, and culturally adaptive models. Full article

Human-centric manufacturing is reshaping collaborative production systems by repositioning human capabilities, safety, experience, and well-being as central concerns in the design and operation of intelligent manufacturing. As manufacturing moves toward Industry 5.0, task allocation in assembly-oriented collaborative systems is no longer only a matter of productivity, cycle time, or resource utilization, but also a key mechanism for protecting worker safety, workload balance, ergonomic compatibility, and long-term well-being. Although existing reviews have addressed various aspects of collaborative manufacturing and ergonomics, a systematic synthesis of how ergonomics is embedded into task allocation for collaborative assembly remains limited. To address this gap, this paper systematically reviews 95 studies identified from WoS and Scopus using an expanded keyword-based search strategy, with April 2026 retained as the publication eligibility cutoff. Studies were included when ergonomics or related human-factor considerations materially influenced task allocation, task assignment, planning, scheduling, or line-balancing decisions in AI-enabled and robot-assisted collaborative manufacturing, with emphasis on assembly-related settings such as workstations, workcells, and assembly lines. The literature is analyzed from four perspectives: ergonomic objectives, allocation scenarios, temporal responsiveness, and computational approaches. Given the heterogeneity of modeling, optimization, simulation, and design studies, a narrative synthesis rather than meta-analysis was conducted. The results show that physiological ergonomics remains the dominant dimension, accounting for 70 of the 95 studies. Recent studies increasingly incorporate multidimensional ergonomic risks, fatigue progression, worker trust, human preference, and real-time human-state information into allocation decisions. The reviewed studies also indicate a transition from static and assessment-informed allocation toward adaptive, state-aware, and cyber-physical allocation. Finally, the review identifies future directions concerning multidimensional ergonomic modeling, assessment-to-decision transformation, real-time adaptive allocation, human-centric interaction, and transferable industrial validation for collaborative assembly systems. No review registration was undertaken. Full article

Robotic welding has been widely used to improve manufacturing efficiency. However, for small batches or one-off jobs, the time and effort required for robotic welding may be economically prohibitive. An intuitive ‘mimicking’-like robotic welding approach can help non-robotics experts instruct the robot to perform the welding operations by letting them demonstrate the welding path via hand gestures without requiring any programming. In this paper, we present a human–robot interaction (HRI)-based weld seam detection for such a robotic welding application. Our approach consists of a vision-based hand detection and tracking method for the user to demonstrate the welding path to the robot’s vision system. We then isolated the welding seam lines and developed a search algorithm to identify the welding paths for the robot. The continuous weld seam path is observed within the bounds of the seam edge in the image and is projected to the robot coordinate space. The seam detection is thoroughly tested with a real-world application on the UR10e robot. The evaluation has revealed an accuracy of 1 pixel in the image plane, equivalent to 1 mm in physical space in our setup. Full article

Unmanned aerial vehicles (UAVs) are increasingly used in applications such as inspection and search and rescue, yet safe and intuitive teleoperation remains challenging in cluttered and GPS-denied environments. This paper presents a modular haptic teleoperation framework that integrates Unity, ROS2, optical motion capture, a physical UAV platform, and a stylus-based haptic device for bidirectional human–robot interaction. Operator inputs are mapped to UAV velocity commands, while obstacle proximity is rendered as continuous haptic feedback to enhance spatial awareness. A Control Barrier Function (CBF)-based command filtering layer is incorporated to modify unsafe velocity commands in real time. The system is evaluated through both Unity-based simulation and real-world experiments using a DJI Tello UAV and OptiTrack motion capture. In the virtual experiments, four conditions were compared: baseline, CBF only, haptic only, and CBF + haptic. The combined CBF + haptic condition reduced the average task completion time from 62.9 s to 42.8 s and resulted in no observed collisions under the evaluated virtual scenarios. The real-world experiments further confirmed stable force–distance behavior, bounded latency, and feasible haptic-assisted UAV navigation in a constrained indoor environment. These results indicate that combining haptic feedback with CBF-based safety control can improve teleoperation efficiency, safety, and usability under the tested conditions while providing a practical step toward simulation-to-real haptic UAV teleoperation. Full article

Haptic technology restores the sense of touch to robotic systems and has become increasingly important for safe and intuitive human–robot interaction in healthcare. Despite substantial advances over the past two decades, widespread clinical adoption remains limited, highlighting a persistent gap between laboratory research and real-world medical deployment. This review synthesizes research from robotics, human–computer interaction, neuroscience, and clinical medicine based on a systematic literature search conducted in IEEE Xplore, PubMed, and Scopus (2000–2025). The review adopts an information-centric perspective, focusing on the clinically relevant information conveyed through haptic feedback rather than force reproduction alone. The review examines tactile, kinesthetic, and hybrid feedback modalities; summarizes key principles of haptic rendering, stability, and control; and evaluates applications in surgical robotics, teleoperation, rehabilitation, prosthetics, and medical training. Evidence indicates that haptic feedback can improve performance, reduce excessive forces, and enhance situational awareness, although benefits remain task-dependent. Clinical translation continues to be constrained by sensing limitations, miniaturization challenges, stability requirements, human factors, and regulatory considerations. Current research is increasingly directed toward sensorless force estimation, artificial intelligence-assisted haptic rendering, wearable and soft haptic interfaces, and neurohaptic technologies, reflecting a shift toward task-oriented and information-centric feedback. Future progress will depend less on maximizing physical realism and more on delivering clinically meaningful information through stable, interpretable, and user-centered haptic systems. This review provides a roadmap for advancing clinically deployable haptic technologies in healthcare. Full article

Automating activities in unstructured environments, such as construction sites, has been challenging due to unpredictable events, limiting robot adoption compared to structured settings. Recently, pre-trained foundation models, particularly Large Language Models (LLMs), have shown promise in addressing this challenge through superior generalization capabilities. This study employed a multi-dimensional method that systematically reviews the field from different perspectives of foundation models in robotics and unstructured environments, and synthesizes them with deliberative acting theory. The findings revealed that LLMs’ linguistic capabilities are primarily used to improve perception and human–robot interactions in robotic tasks, while applications in project management, safety, and natural hazard detection are the most utilized applications of foundation models in unstructured environments. Our synthesis shows an empirical gap in the field where fewer identified studies within unstructured environments validated their foundation model applications using physically deployed robots. We positioned the current state-of-the-art on a five-level automation scale of conditional automation. These findings inform future scenarios, challenges, and solutions toward autonomous safe unstructured environments. Our study serves as a benchmark to track our progress toward that future. Full article

We present a neuroadaptive control framework applied to a tactile sensing interface for real-time, human-guided physical interaction with a robotic arm. The framework employs a dual-loop architecture consisting of an inner-loop neuroadaptive controller that compensates for nonlinear robot dynamics and an outer-loop ARMA–RLS tactile mapping that converts tactile sensor voltages into planar end-effector displacement commands. Four piezoresistive tactile sensors mounted on the robot end-effector are calibrated individually using autoregressive moving-average (ARMA) models updated through recursive least squares (RLS). The proposed tactile interface does not estimate an absolute Cartesian force/torque wrench; instead, it learns a user- and sensor-specific voltage-to-motion command mapping for planar guidance. To evaluate robustness to user variability, 28 participants completed the calibration experiments, producing 112 user- and sensor-specific calibration models. The calibration procedure achieved millimeter-level displacement-prediction accuracy, with a mean RMSE of approximately 2.70 mm across participants. After calibration, participants used the tactile interface to guide the robot along a predefined figure-eight trajectory. The average nearest-path tracking error decreased from $11.07\pm 5.45$ mm in the initial trial to $8.41\pm 3.48$ mm in the final trial, indicating improved tactile-guided path following after repeated exposure to the interface. During these experiments, the inner neuroadaptive controller maintained bounded joint-space tracking errors. Overall, the proposed calibration and control framework provides a low-cost physical interface for planar human-guided robot motion without requiring a wrist-mounted force/torque sensor. Full article

Large language models (LLMs) are increasingly being explored for integration into sensor-driven control systems across robotics, industrial automation, energy infrastructure, healthcare, smart environments, and other sensor-rich domains. This review synthesizes emerging research from the perspective of sensor-driven control systems, defined as systems in which sensing is substantively linked to monitoring, estimation, supervision, planning, decision-making, or actuation. Rather than treating LLMs as generic intelligent agents, the review examines their position within the sensing–decision–control chain and their interaction with state representations, supervisory logic, human operators, external tools, and classical control components. The paper develops a functional taxonomy of LLM roles based on proximity to actuation, grounding requirements, and deployment risk. This taxonomy reveals a clear maturity gradient: interpretive, supervisory, diagnostic, and engineering-support roles are currently the most credible and deployable, whereas runtime control participation remains the least mature and highest-risk form of integration. The analysis further shows that reliable implementations are predominantly hybrid. In such architectures, LLMs function as semantic and orchestration layers that augment, rather than replace, classical sensing, estimation, planning, and control. Key integration patterns include sensor-to-semantics pipelines, retrieval-augmented generation, tool use, agentic workflows, closed-loop refinement, and safety-aware mechanisms. Persistent challenges—including hallucination, weak physical grounding, latency, cybersecurity risks, and the lack of formal guarantees—highlight the need for rigorous operational evaluation and realistic benchmarks. The review concludes that LLMs are most credible as interpretive, supervisory, diagnostic, and human-facing intelligence layers embedded within hybrid architectures. Future progress will depend on deeper neuro-symbolic integration, efficient local deployment, human-centered autonomy, and stronger evaluation practices that preserve the strengths of classical control engineering while extending them with semantic reasoning and supervisory intelligence. Full article

Industry 4.0, expected to limit the burden of manual labor through the integration of cyber-physical systems, the Internet of Things (IoT), and machine learning methods, failed to meet social expectations. It started excluding humans from the production process. The next stage of the industrial revolution, Industry 5.0, reverses this trend by emphasizing the importance of human involvement and interaction in production processes. In this paper, we present the evolution of robotic systems, from those of Industry 4.0 to their humanized versions expected in Industry 5.0, with a particular emphasis on system cybersecurity. Moreover, we present the challenges and business opportunities that telecommunications operators face in implementing and operating robotic cyber-physical systems. We also analyze new security challenges arising from this transformation and the central role of humans in industrial processes. We illustrate the identified problems with a special case: Cobots. Full article

This paper proposes a safe and effective human–robot physical interaction control framework for exoskeleton robots that enhances system compliance and safety while enabling the robot to adapt to human motion. The framework is designed around two primary objectives: first, a model-free adaptive control method is employed for reference trajectory estimation to achieve real-time estimation of human motion intention; second, the Forgetting Factor Recursive Least Squares (FFRLS) method is utilized for online estimation and the learning of human impedance parameters, considering their time-varying nature. In addition, a model-free adaptive trajectory tracking control strategy is proposed to optimize control performance during human–robot physical interaction. Simulation results demonstrate that the proposed control framework outperforms conventional methods significantly in terms of safety and compliance. Full article

This study presents a compact affective sensing system that converts physical touch into intuitive multimodal feedback through dynamic facial expressions and optional audio responses. The system was developed to support non-verbal, human-centered interaction in embedded human–machine interfaces, where tactile input can be directly associated with emotional perception. The hardware platform is based on the M5Stack CoreS3, integrating a force-sensitive resistor (FSR), an ESP32-S3 microcontroller, an embedded LCD, and a built-in speaker. Pressure signals are acquired using a simple voltage divider circuit and digitized through the built-in 12-bit analog-to-digital converter (ADC) of the ESP32-S3. To improve signal stability, a simple moving average (SMA) filter is applied for noise reduction. The normalized pressure signal is classified into multiple pressure regions and mapped to emotional states. Smooth facial transitions are generated by continuously interpolating geometric facial parameters, including mouth curvature, eye shape, and eyebrow angle, without relying on pre-rendered images. Experimental evaluation demonstrated stable pressure detection, low-latency response, and intuitive emotional feedback across a wide operating range. User evaluation results further indicated that the combination of visual and auditory feedback enhanced realism, anthropomorphic perception, and interaction quality. The proposed system demonstrates the potential of tactile affective sensing for applications in assistive communication, education, and empathetic human–robot interaction systems. Full article

Achieving safe physical interaction on the human back is challenging due to respiratory rhythms, complex topography, and varying tissue stiffness. To enable compliant force tracking within commercial closed position-control robot architectures, this paper presents an adaptive variable damping admittance control framework driven by multi-dimensional force sensor feedback. A stiffness-free admittance model is constructed to eliminate steady-state tracking errors, integrated with a nonlinear adaptive damping law that sensitively responds to real-time force sensor measurements. This mechanism rapidly dissipates dynamic impact energy during contacts while maintaining low impedance during steady state. Validated via a high-fidelity MATLAB R2024b-CoppeliaSim co-simulation platform replicating Traditional Chinese Medicine (TCM) manipulations, the proposed sensor-driven strategy significantly improves force tracking fidelity over traditional fixed-parameter control. Quantitative results demonstrate that across all complex therapeutic waveforms, the root mean square error (RMSE) remains below 0.42 N, the mean absolute error (MAE) is within 0.32 N, and the squared correlation coefficient ($r^2$) exceeds 0.97. These findings confirm the high efficiency and clinical potential of the proposed framework. Full article