Search Results (200)

This paper presents a low-cost retrofitting pipeline for a legacy industrial robot that uses a single RGB webcam and monocular 2D keypoint tracking to estimate human-arm posture angles ${\mathit{\theta }}^{\left(\mathrm{h}\right)}$ and map them to robot-axis joint targets ${\mathbf{q}}_{\mathrm{cmd}}^{\left(\mathrm{r}\right)}$ for A1–A3 on a KUKA KR5-2 ARC HW, while keeping the wrist orientation (A4–A6) fixed. Rather than targeting full six-DoF manipulation, the main contribution is an experimental characterization of how far monocular 2D posture-to-axis mapping can be used reliably for coarse placement and safeguarded low-speed demonstrations on a legacy robot platform. Vision-side accuracy was evaluated per axis against goniometer-based reference angles ${\mathit{\theta }}_{\mathrm{ref}}^{\left(\mathrm{h}\right)}$, showing low errors for A2–A3 within the tested range and larger errors for A1 due to monocular yaw/depth ambiguity and occlusions. The study also analyzes failure modes during simultaneous multi-joint motion, where performance degrades notably, especially for A2 and A3, and reports practical mitigation directions such as improved viewpoints, multi-view/depth sensing, and stricter dropout handling. Runtime behavior is additionally characterized through a loop timing budget, with an end-to-end latency of 185.44 ms and an effective loop frequency of 5.39 Hz, which is consistent with low-speed online operation within the demonstrated scope. The system was implemented in a fenced industrial cell with restricted access and emergency stop; no collaborative operation is claimed. Full article

In response to the redundant spatio-temporal modeling and insufficient adaptation to dynamic decision-making in eye-tracking interaction of smart home interfaces, a smart home interface eye-tracking response optimization model based on spatio-temporal Transformer and gate control cross-attention is proposed. It adapts the physiological characteristics of eye-tracking jumps through dynamic sparse attention gating to compress computational redundancy and combines multi-objective reinforcement learning attention modulation to construct a closed-loop decision-making mechanism, optimizing interface parameters in real-time. Experiments showed that the model reduced eye-tracking trajectory prediction error by 23.7% compared to advanced benchmarks, increased the success rate of adapting to dynamic mutation scenarios to 89.2%, and controlled performance fluctuations within 2.3% under noise interference. In high-fidelity user testing, the accuracy of cross-task gaze transfer reached 93.4%, the failure rate of glare interference was optimized to 2.4%, and the user cognitive load index was reduced by 27.9%. Its resource consumption and energy consumption were reduced by 26.7% and 44.9%, respectively, while its posture deviation tolerance remained at 3.5°. The sparse spatio-temporal modeling of the spatio-temporal adaptive Transformer module and the enhanced gating mechanism of the hierarchical gated cross-attention module work together to break through the limitations of traditional methods in computational efficiency and dynamic feedback, providing high-precision and low-latency eye-tracking interaction solutions for smart home interface systems, and promoting the practical evolution of personalized human–machine collaborative control. Full article

Human-to-robot (H2R) handovers are critical in human–robot interaction but are challenged by complex environments that impact robot perception. Traditional RGB-based perception methods exhibit severe performance degradation under harsh lighting (e.g., glare and darkness). Furthermore, H2R handovers occur in unstructured environments populated with fine-grained visual details, such as multi-angle hand configurations and novel object geometries, where conventional semantic segmentation and grasp generation approaches struggle to generalize. To overcome lighting disturbances, we present an H2R handover system with a dual-path perception pipeline. The system fuses perception data from a stereo RGB-D camera (eye-in-hand) and a time-of-flight (ToF) camera (fixed scene) under normal lighting, and switches to the ToF camera for reliable perception under glare and darkness. In parallel, to address the complex spatial and geometric features, we augment the Point Transformer v3 (PTv3) architecture by integrating a T-Net module and a self-attention mechanism to fuse the relative positional angle features between human and robot, enabling efficient real-time 3D semantic segmentation of both the object and the human hand. For grasp generation, we extend GraspNet with a grasp selection module optimized for H2R scenarios. We validate our approach through extensive experiments: (1) a semantic segmentation dataset with 7500 annotated point clouds covering 15 objects and 5 relative angles and tested on 750 point clouds from 15 unseen objects, where our method achieves 84.4% mIoU, outperforming Swin3D-L by 3.26 percentage points with 3.2× faster inference; (2) 250 real-world handover trials comparing our method with the baseline across 5 objects, 5 hand postures, and 5 angles, showing an improvement of 18.4 percentage points in success rate; (3) 450 trials under controlled adverse lighting (darkness and glare), where our dual-path perception method achieves 82.7% overall success, surpassing single-camera baselines by up to 39.4 percentage points; and (4) a comparative experiment against a state-of-the-art multimodal H2R handover method under identical adverse lighting, where our system achieves 75.0% success (15/20) versus the baseline’s 15.0% (3/20), further confirming the lighting robustness of our design. These results demonstrate the system’s robustness and generalization in challenging H2R handover scenarios. Full article

This paper proposes an energy-based training assistance controller for a unicycle riding simulator inspired by Human Adaptive Mechatronics (HAM). We focus on sagittal plane (pitch) balance for beginners and derive a simplified longitudinal plane unicycle model, where pedaling is represented as an action–reaction torque between the wheel and the rider–saddle body. After time normalization, the saddle dynamics is expressed in a form suitable for energy analysis. Using the natural Hamiltonian of the uncontrolled system, we design a minimum-intervention pumping–damping controller that modifies the energy flow only when necessary. The assistance is smoothly activated outside a training core region defined by a saddle-angle bound: a damping term suppresses excessive motion, and a pumping term prevents trapping in a tilted posture when the energy becomes too small. The proposed framework offers physically interpretable, localized assistance while preserving the natural unicycle dynamics required for skill learning. Full article

Postural balance is a foundational component of human motor behavior, yet it remains conceptually ambiguous and methodologically heterogeneous across the clinical, educational, and sport sciences. This narrative review aims to provide an integrative framework that clarifies key concepts (postural control vs. postural balance), synthesizes the main sensorimotor and biomechanical mechanisms underpinning balance, and organizes current assessment approaches and functional implications across populations. Narrative literature synthesis was conducted to integrate evidence covering multisensory integration and sensory reweighting, central neural control (spinal, brainstem, cerebellar, and cortical contributions), neuromuscular and biomechanical strategies (e.g., ankle/hip/stepping), and cognitive influences (e.g., dual-task effects). We further summarize commonly used instrumental outcomes derived from force-platform center-of-pressure metrics and widely adopted clinical and functional balance tests, highlighting their typical applications and limitations across the lifespan including pediatric, general adults, older adults, and athletic populations. This review proposes a closed-loop, systems-based model in which postural balance is conceptualized as an emergent functional outcome arising from distributed postural control processes shaped by task, environmental, and individual constraints. In conclusion, integrating mechanistic understanding with population-specific assessment enhances interpretability and supports more precise, context-sensitive balance evaluation and intervention in both health and performance settings. Full article

Muscle onset detection is a fundamental problem in electromyography signal analysis, human–machine interaction, and rehabilitation assessment. In medical and biomedical applications, slow muscle activation onset processes are widely encountered in scenarios such as rehabilitation training, postural regulation, and fine motor control. Such processes are typically characterized by slowly varying amplitudes, long temporal durations, and high susceptibility to noise interference, which poses significant challenges for accurate identification of onset timing. To address these issues, a lightweight temporal attention method for slow muscle activation onset detection is proposed and systematically validated under multimodal experimental settings. The proposed method takes surface electromyography signals as the primary input, while synchronously acquired optical motion image data are incorporated into the experimental design and result analysis, thereby aligning with the common joint use of optical imaging and physiological signals in medical and biomedical research. From a methodological perspective, the proposed framework is composed of lightweight temporal feature encoding, a slow activation-aware temporal attention mechanism, and noise suppression with stable decision strategies. Under the constraint of low computational complexity, the ability to model progressive activation signals is effectively enhanced. Experiments are conducted on a dataset containing multiple types of slow activation movements, and model performance is evaluated using five-fold cross-validation. The results demonstrate that under regular signal-to-noise ratio conditions, the proposed method significantly outperforms traditional threshold-based approaches, classical machine learning models, and several deep learning baselines in terms of onset detection accuracy, recall, and precision. Specifically, onset detection accuracy reaches approximately $92\%$, recall is around $90\%$, and precision is approximately $93\%$. Meanwhile, the average onset detection error and detection delay are reduced to about $41\mathrm{ms}$ and $28\mathrm{ms}$, respectively, with the false positive rate controlled at approximately $2.2\%$. Stable performance is further maintained under different noise levels and cross-subject settings, indicating strong robustness and generalization capability. Full article

Background: Pumping in Laser-class sailing is a dynamic propulsion technique used in marginal wind conditions and characterized by repetitive, coordinated oscillations of the sailor–sail system. Despite its practical relevance, its biomechanical and ergonomic demands remain insufficiently characterized. Methods: A mixed-methods framework was applied combining questionnaire data, kinematic analysis, ergonomic assessment, and musculoskeletal modelling. Thirty-six competitive Laser sailors completed a Borg CR-10-based questionnaire on perceived discomfort/fatigue across body regions at predefined time points (during pumping, immediately after training, and the following day). A controlled land-based multi-angle video acquisition was used to reconstruct a standardized pumping posture and parameterize a digital human model in DELMIA^® for postural/kinematic analysis. Ergonomic risk was assessed using REBA, and muscle activity was estimated using the AnyBody^® Modeling System (simulation-derived normalized muscle activity across 129 muscles). Results: the simulation identified high neuromuscular demand in the trunk and shoulder complex, with several deep trunk stabilizers and the left latissimus dorsi reaching 100% modeled normalized muscle activity. Marked lateral asymmetry was observed, with right-sided trunk dominance and left-sided shoulder dominance. Kinematic analysis showed substantial joint excursions, with large lumbar motion amplitudes, while REBA yielded a score of 11 (Very-High Risk). Questionnaire data indicated a high prevalence of pumping-related musculoskeletal discomfort (72.2%), most frequently involving the lower back, shoulders, and knees. A dissociation was observed between modeled muscle activity and perceived fatigue, with the lower limbs rated as most fatigued despite lower modeled activation than the trunk. Conclusions: Findings identify the deep trunk stabilizers, latissimus dorsi, and lower extremities as key regions involved in pumping, with marked lateral asymmetry and high ergonomic risk. They support targeted training, injury-prevention, and ergonomic strategies to improve performance and reduce injury risk in competitive sailing. Full article

In the era of Industry 4.0, artificial intelligence technology is experiencing rapid development, and the integration of artificial intelligence (AI) with flexible sensors has emerged as a transformative approach for human motion and posture sensing. This paper explores the advancements in AI-enhanced flexible sensors, focusing on the application of flexible sensors on various parts of the human body. Flexible sensors, due to their conformability and sensitivity, are ideal for capturing the dynamic and subtle movements of the human body. AI algorithms, particularly machine learning and deep learning techniques are employed to process the complex data streams from these sensors, enabling the accurate recognition and prediction of various human postures and motions. The combination of these technologies overcomes the limitations of traditional sensing systems, offering higher precision, adaptability, and real-time feedback. It can be applied to healthcare for rehabilitation monitoring, sports for performance enhancement, and human–computer interaction for intuitive control. This review also discusses the challenges such as sensor reliability, data privacy, and power management. The future outlook emphasizes more sophisticated AI models and deeper technology integration, promising a seamless integration into everyday life for enhanced human–machine interaction and health monitoring. Full article

A safe physical human–robot interaction (pHRI) in rehabilitation requires reliable perception and low-latency decision making under heterogeneous and unreliable sensor inputs. This paper presents a multimodal sensor-fusion-based safety framework that integrates physical state estimation, semantic information fusion, and an edge-deployed large language model (LLM) for real-time pHRI safety control. A dynamics-based virtual sensing method is introduced to estimate internal joint torques from external force–torque measurements, achieving a normalized mean absolute error of $18.5\%$ in real-world experiments. An asynchronous semantic state pool with a time-to-live mechanism is designed to fuse visual, force, posture, and human semantic cues while maintaining robustness to sensor delays and dropouts. Based on structured multimodal tokens, an instruction-tuned edge LLM outputs discrete safety decisions that are further mapped to continuous compliant control parameters. The framework is trained using a hybrid dataset consisting of limited real-world samples and LLM-augmented synthetic data, and evaluated on unseen real and mixed-condition scenarios. Experimental results show reliable detection of safety-critical events with a low emergency misdetection rate, while maintaining an end-to-end decision latency of approximately 223 ms on edge hardware. Real-world experiments on a rehabilitation robot demonstrate effective responses to impacts, user instability, and visual occlusions, indicating the practical applicability of the proposed approach for real-time pHRI safety monitoring. Full article

The increasing adoption of data-driven techniques in cybersecurity has introduced new opportunities to enhance detection, response, and automation capabilities within the cybersecurity ecosystem; however, cybersecurity auditing remains constrained by traditional compliance-oriented approaches that rely profoundly on binary, checklist-based evaluations. Such approaches often reinforce a policing or “sheriff-style” perception of auditing, emphasizing enforcement rather than enablement, risk insight, and organizational improvement. Of primary concern is that the “sheriff-style” cybersecurity audit approach often fails to accurately portray the true state of an organization’s cybersecurity posture, often providing a misleading sense of assurance based solely on formal compliance and controls existence. This study proposes an Anti-Sheriff Cybersecurity Audit Model, that moves beyond cybersecurity control checklists, by integrating intelligence-informed risk assessments with structured human judgment to support a more robust, adaptive, and risk-oriented auditing process. Grounded in design science research (DSR), the proposed approach combines conventional binary compliance verification with intelligence-derived risk indicators and governance-based maturity assessments to evaluate cybersecurity controls across technical, operational, and organizational dimensions. The approach aligns with established standards and frameworks, including International Organization for Standardization and the International Electrotechnical Commission (ISO/IEC) 27001, the National Institute of Standards and Technology (NIST), and the Center for Internet Security (CIS) benchmarks, while extending their application beyond static compliance validation. A fictional case study is used to demonstrate the model’s applicability and to illustrate how hybrid scoring can reveal residual risk not captured by conventional cybersecurity audits. The findings indicate that combining intelligence-informed analytics with structured human judgment enhances audit depth, interpretability, and business relevance. The proposed approach, therefore, provides a foundation for evolving cybersecurity auditing from just periodic compliance assessments, toward a continuous, risk-informed, and governance-aligned assurance system. Full article

Traditional ergonomic considerations in human–machine and human–swarm systems have primarily relied on static diagnostic snapshots, which often fail to capture the temporal accumulation and non-linear dissipation of musculoskeletal fatigue. As Industry 5.0 transitions toward immersive, human-centric cyber-physical systems, redefining ergonomic load as an endogenous state variable allows for real-time control of musculoskeletal integrity. This work proposes the Dynamic Integrity Governor (DIG) framework, which treats ergonomic load as a normalized, dimensionless state variable $\xi \left(t\right)$ that evolves according to a stochastic proxy of recursive Newton–Euler dynamics. Leveraging a machine-perception-aware Adaptive Event-Triggered Mechanism (AETM) and the Multi-modal Flamingo Search Algorithm (MMFSA), we develop a decentralized architecture that redistributes ergonomic demands in real-time. The framework utilizes a 7-DOF kinematic model and Control Barrier Functions (CBF) to maintain human–swarm interaction within safe biomechanical boundaries, effectively filtering stochastic sensor noise through Girard-based stability buffers. Computational validation via N = 1000 Monte Carlo runs demonstrates that the proposed strategy achieves a 79.97% reduction in control updates (SD = 0.19%; p < 0.0001; Cohen’s d = 2.41), ensuring a positive minimum inter-event time (MIET) to prevent the Zeno phenomenon and supporting carbon-aware AI operations. The integration of variable prediction horizons yields an 80.69% improvement in solving time, while ensuring a minimal computational footprint suitable for real-time edge deployment. The identification of optimal postural niches maintains peak ergonomic load at 41.42%, representing a significant safety margin relative to the integrity barrier. While validated against a 50th percentile male profile, the DIG framework establishes a modular foundation for personalized ergonomic governors in inclusive Industry 5.0 applications. Full article

Understanding how seat-induced whole-body vibration (WBV) is transmitted to and actively compensated by the human body is essential for accurately assessing discomfort, fatigue, and postural control in vehicle occupants. This study proposes a visual–inertial fusion framework utilizing IMU-RGB-D data to isolate seated human body vibration in dynamic vehicular environments. In real-cabin monitoring systems, measured motion is a superposition of platform vibration, passive transmission through the body, active postural compensation, and camera jitter. Existing WBV and driver monitoring studies typically rely on single modality sensing, such as inertial or visual approaches, without decomposing these components or modelling camera vibration. The framework synchronized three IMUs with RGB-D landmarks. Seat, human body, and camera accelerations are separated, and body vibration velocity is derived from body–seat differential acceleration via band-pass filtering and spectral integration. The 3D landmarks enable rotational-translational Postural Compensation Index metrics, axis-wise energy distributions, and anthropometric consistency checks. The study is held in an in-service urban tram case. Torso vibration is dominated by 40% anteroposterior components, while head postural is predominantly > 50% lateral sway. Near static anthropometric evaluation was also studied, resulting in shoulder width errors that remain within ±10–20 mm. The results show that the framework can distinguish passive ride phases from strongly compensated phases, separate camera jitter from true body motion, and reveal anisotropic postural strategies, providing a structured basis for vibration and posture analysis in in-vehicle monitoring. Full article

Maritime search and rescue (SAR) operations are challenged by vast search areas, poor visibility, and the time-critical nature of victim survival, particularly in dynamic coastal areas. This study presents an intelligent unmanned aerial vehicle (UAV) framework for real-time detection, tracking, and prioritization of people in distress at sea. Unlike existing UAV-based SAR systems that rely on visual sensing or offline human intervention, the proposed framework integrates RGB-thermal multimodal sensing and posture recognition to enhance victim prioritization and survivability estimation. Visual-thermal data support human posture detection, inference of physiological indicators, and autonomous UAV navigation. Metadata are transmitted to a ground control station to enable adaptive altitude control, trajectory rejoining, and multi-target prioritization. Field-inspired experiments in Quang Ninh Province, Vietnam demonstrated robust real-time performance, achieving 23 FPS with detection accuracy up to 84% for swimming subjects and over 50% for drowning postures. These findings demonstrate that Edge-AI-enabled UAVs can serve as a practical and efficient solution for maritime SAR, reducing response times and improving mission outcomes. Full article

Utilizing video surveillance in mines to identify unsafe behaviors of miners is an important technical means for preventing coal mine accidents and achieving safety control. However, the complex underground environment (such as chaotic backgrounds, personnel occlusion, etc.) severely affects the estimation of human postures and feature extraction, resulting in low accuracy of unsafe behavior identification. To address this issue, this paper proposes a miner unsafe behavior recognition algorithm based on improved AlphaPose (RS-AlphaPose). Firstly, the improved real-time detection Transformer (RTDETR) is adopted to replace the original target detection network. Through the deformable attention mechanism and the addition of small target detection layers, the target detection ability in complex scenes is enhanced. Secondly, the sliding window attention and channel attention mechanisms are integrated in the posture estimation network to strengthen multi-scale semantics and global context correlation, thereby improving the accuracy of skeleton extraction in the presence of occlusion. Finally, the spatio-temporal graph convolution network is introduced to construct the spatio-temporal dependency of the skeleton sequence, capturing the temporal features of dynamic behaviors. On the COCO2017 posture dataset, the average accuracy of posture estimation of this algorithm reaches 72.5%, which is 2.2% higher than the basic AlphaPose model. On the self-built miner dynamic behavior dataset, the average recognition accuracy for typical unsafe behaviors such as climbing and crossing reaches 94.5%, which is 4.5% higher than the basic model. The experiments show that the proposed algorithm can effectively solve the interference problems in complex underground environments, significantly improve the accuracy of dynamic unsafe behavior recognition of miners, and provide a reliable technical solution for coal mine safety production. Full article

Most pediatric exoskeletons for cerebral palsy (CP) focus on lower-limb assistance and neglect trunk control, limiting rehabilitation outcomes. This study presents a self-aligning trunk–limb exoskeleton that integrates trunk stabilization with active lower-limb support. The design includes a hip–waist rapid adjustment mechanism, a bioinspired gear-rolling knee joint, modular thigh–shank structures, a trunk support module, and a body-weight support device. To enable transparent and coordinated assistance under pathological gait conditions, a continuous gait progress-based multi-joint control framework is developed. Joint motion is described as continuous gait progress over the full gait cycle (0–100%), and joint-specific progress estimates are fused into a unified system-level reference using observability-weighted circular statistics. Inter-joint coordination is achieved through phase-consistency-based temporal modulation implemented, enabling smooth synchronization while preserving joint-level autonomy and motion continuity. Technical evaluation—comprising kinematic misalignment analysis, simulation validation, and gait trials—demonstrated a 66.8% reduction in hip misalignment and an 87.4% reduction in knee misalignment. Gait parameters under exoskeleton-assisted walking closely matched baseline walking, confirming natural kinematic preservation without interference. These results indicate that the proposed trunk–limb exoskeleton improves human–robot synergy, enhances postural stability, and provides a promising solution for pediatric gait rehabilitation in CP. Full article