Search Results (544)

Maintaining reliable communication while ensuring collision-free motion is a central challenge for mobile relay robots operating in indoor disaster environments, where abrupt non-line-of-sight (NLOS) degradation and narrow structural bottlenecks can severely disrupt multi-hop connectivity. To address this problem, this paper proposes a Gaussian Process-Driven Adaptive Tube Model Predictive Control (GP-ATMPC) framework for communication-preserving relay navigation. Gaussian process regression (GPR) is used to construct a probabilistic spatial radio map from sparse received signal strength indicator (RSSI) measurements, providing both the predicted channel mean and its uncertainty over unvisited regions. Motion uncertainty is represented by an adaptive ellipsoidal error tube whose radius varies with translational motion, angular motion, and localization uncertainty. Based on this tube model, both obstacle and communication constraints are tightened over the full closed-loop state tube via a tube-tightened lower confidence bound (LCB) that jointly accounts for radio-prediction and motion-tracking uncertainty. Across two indoor disaster environments and 50 Monte Carlo runs each, the proposed method attains the highest connectivity satisfaction rate among controllers that preserve a safe motion margin, with significantly fewer end-to-end connectivity violations than nominal and heuristic adaptive-margin MPC by a paired Wilcoxon test, while maintaining millisecond-level online solve times. A reactive connectivity-first baseline reaches slightly higher raw connectivity but at three to four times the near-collision rate and without feasibility or stability guarantees. The radio-prediction layer is further validated in a higher-fidelity Gazebo environment and on real indoor RSSI measurements, where it reconstructs the measured channel with a mean absolute error of about 2.1 dB. These results indicate that coupling spatial radio prediction with adaptive tube-based robust control provides an effective framework for resilient communication-aware relay navigation in degraded indoor environments. Full article

Accurate and reliable localization is a fundamental requirement for autonomous mobile robots operating in structured indoor environments. Adaptive Monte Carlo Localization (AMCL), widely used due to its probabilistic flexibility, suffers from performance degradation in challenging situations such as low-motion, sensor degradation, symmetry ambiguity, and abrupt position changes (kidnapped robot). This study proposes the Confidence-Gated Virtual Scan Motion AMCL (CG-VSM-AMCL) approach, which extends the standard AMCL structure with a selective and confidence-based posterior enhancement mechanism to overcome these limitations. The proposed method integrates beam partitioning, cluster-based dominance analysis, observability-aware gating, and recovery-driven adaptive particle injection components within a holistic architecture. The method was evaluated on a structured department map under seven representative scenarios: cold-start, low-motion, kidnapped robot recovery, odometry bias, scan dropout, world–model mismatch, and symmetry ambiguity. Experimental results demonstrate that the proposed approach systematically reduces localization error, false-lock rate, and convergence time compared to basic AMCL variants, and improves stability under challenging conditions. The significant improvements achieved, particularly in low-motion and symmetry-containing environments, reveal that selectively activated correction strategies can substantially increase localization robustness without altering the fundamental probabilistic structure of AMCL. Full article

Structural magnetic resonance imaging (sMRI) is progressively used to diagnose brain diseases; however, brain sMRI scans can be easily corrupted by artifacts, e.g., motion artifacts. To remove artifacts, deep learning (DL) algorithms have been extensively studied recently. However, their performance and the challenges currently faced in clinical practice (e.g., real-world robustness, hallucination and over-smoothing) have not been adequately studied in a quantitative manner. In this structured literature review, we quantitatively examined DL-based artifact correction studies (N = 30), retrieved from the major databases (i.e., Google Scholar, PubMed, Web of Science, and Scopus), which particularly focused on clinical-field-strength (defined as 1.5 Tesla (T) and above) sMRI in a non-pediatric setting. Our review suggests that current DL-based approaches exhibit promising fidelity measured by structural similarity (SSIM, 0.92 ± 0.05) index and peak signal-to-noise ratio (PSNR, 32.85 ± 4.53 dB). In addition, We identified the factors underlying hallucination or over-smoothing, which are associated with neural network (NN) architecture and the training process. This study also reveals the potential advantages, brought about by frequency-aware NN. Finally, we outline several future directions, including an emerging paradigm in DL, namely physics-informed NN (PINN). Full article

Accelerometer sensors and artificial intelligence (AI) are reshaping automated behavior monitoring in precision livestock management, yet their joint deployment on extensive rangelands is constrained by energy and bandwidth budgets. Low-Power Long-Range Wide-Area Network (LoRaWAN) collars address these constraints by compressing the raw tri-axial signal on the device into a single scalar per reporting interval, the Motion Index (MI). This onboard compression preserves enough signal to separate active behaviors but discards the per-axis and frequency content that fine-grained classification typically relies on. On a dataset of 9222 labeled observations from 24 cows across four breeds, MI distinguishes walking from grazing reliably but fails to separate ruminating from resting; both correspond to a stationary animal and yield near-zero, statistically indistinguishable distributions. Earlier MI-only models reached only about 65% four-class accuracy, and ruminating was commonly merged into resting. We show that much of this loss can be recovered by treating the MI stream as a time series. Session-aware lag features, rolling statistics, and an autoregressive previous-behavior feature lift four-class macro-F1 from 0.647 to 0.94, with per-class F1 of 0.95 for ruminating and 0.92 for resting (and at least 0.92 for every behavior). In autonomous deployment the previous behavior must be predicted rather than observed; for this setting we add a Viterbi sequence-decoding step that combines the classifier’s per-step outputs with a learned behavior-transition model, recovering a substantial part of the ruminating signal from the activity stream alone while keeping walking and grazing reliable. The gain is consistent across seven classifiers and four genetically distinct breeds, indicating that it is driven by the features rather than by a specific model. Full article

Background and Objectives: Robotic-assisted total knee arthroplasty (rTKA) is being increasingly used to improve surgical precision, soft-tissue balancing, and functional recovery. However, evidence comparing rTKA with conventional manual TKA (mTKA) across functional, patient-reported, neuromotor, and safety outcomes remains heterogeneous. Materials and Methods: This narrative (non-systematic) review synthesises studies evaluating functional outcomes, patient-reported outcome measures (PROMs), joint awareness, range of motion (ROM), neuromotor recovery, and complications following rTKA versus mTKA. Study inclusion was based on author judgement and data accessibility. The reviewed evidence included five randomised controlled trials, 9 retrospective studies, six prospective non-randomised studies, two meta-analyses, one cross-sectional study, and one umbrella review, covering CT-based and imageless robotic platforms, including semi-active and active systems such as MAKO, NAVIO, CORI, ROSA, ROBODOC, CUVIS Joint, SkyWalker, TSolution One, AKEC, JIANJIA, and YUANHUA. Results: rTKA consistently demonstrated outcomes comparable to mTKA in PROMs (OKS, KOOS, WOMAC, KSS), with some studies reporting modest early improvements in pain and function. Joint awareness and patient satisfaction showed the most consistent early advantages for rTKA. Early postoperative ROM and neuromotor recovery, including balance and gait symmetry, were improved with rTKA, likely due to enhanced alignment and soft-tissue balancing; however, mid- and long-term outcomes were similar. Complication rates were low and comparable, with robotic-specific issues being rare and self-limited. Conclusions: rTKA provides small but reproducible early benefits in joint awareness, neuromotor function, and patient satisfaction, without clear long-term superiority. These early advantages may translate into meaningful population-level benefits, including faster recovery and potential healthcare cost reduction. Further high-quality studies are needed to assess long-term clinical and economic outcomes. Full article

The proliferation of IoT-based surveillance has caused a sharp rise in video data, straining network bandwidth and cloud storage. Conventional video compression exploits pixel-level redundancy but ignores the semantic importance of content, transmitting large volumes of redundant background. This paper proposes a semantic-aware video offloading framework that improves bandwidth efficiency in cloud-based surveillance. DeepLabV3+ with a ResNet-50 backbone performs semantic segmentation at the edge to extract relevant foreground objects (e.g., pedestrians and vehicles) while suppressing static background. A background reference caching mechanism transmits the static scene once and reuses it at the cloud for full-frame reconstruction, minimizing redundant transmission. On a dataset of 12 surveillance sequences (self-captured videos plus sequences from the CDnet 2014 benchmark), the method achieves up to 74.63% reduction in transmitted data, a 33% improvement in storage efficiency, and a compression ratio of 2.88×, while maintaining an average PSNR of 44.92 dB. Paired t-tests ($p<0.001$) and sensitivity analysis across varying scene dynamics and semantic configurations confirm the robustness of the approach, and comparisons indicate clear gains over conventional motion-based offloading in bandwidth efficiency and reconstruction fidelity. Full article

WiFi channel state information (CSI) has become a compelling sensing modality for contactless human activity recognition. However, differences in datasets, preprocessing protocols and model configurations make consistent comparison and reproducibility challenging. This study presents a unified baseline evaluation of four widely adopted deep learning architectures: multilayer perceptron (MLP), convolutional neural network (CNN), gated recurrent unit (GRU) and a hybrid CNN–GRU model across multiple publicly available CSI datasets encompassing a range of sensing tasks. We harmonize the datasets, implement a standardized preprocessing and training pipeline to reduce experimental inconsistencies and support controlled within-dataset comparisons of model behavior. Evaluations include single-person activity recognition, fall-risk estimation, multiperson occupancy classification and localization-aware activity recognition, representing progressively higher temporal and spatial complexity. Our results show dataset-dependent trends: CNNs provide an efficient accuracy–complexity trade-off in several structured activity scenarios, whereas GRUs are advantageous when temporal dynamics are more prominent, although with greater training and inference costs. In contrast, MLPs generally underperform due to limited capacity to capture spatial and temporal dependencies. Confusion matrix analysis reveals that dynamic behaviors and low-motion states remain challenging to distinguish, underscoring the importance of temporal modeling. By releasing the complete experimental pipeline and benchmarking results, this work establishes a reproducible reference framework for the research community and highlights directions for future investigation, including cross-dataset generalization, hybrid model design and lightweight deployment strategies. Full article

Exchange-rate forecasting requires modelling non-stationary dynamics, heavy-tailed shocks, and complex temporal dependencies. However, forecasting performance in emerging-market currencies is fundamentally constrained by intrinsic dynamical instability, while most existing approaches are evaluated primarily through predictive accuracy rather than the predictability limits of the underlying system. This paper develops a predictability-aware framework that combines nonlinear dynamical diagnostics with a Lévy-driven neural stochastic differential equation model. Drift and diffusion are parameterized by neural networks and driven by $\alpha$-stable Lévy motion, enabling the representation of non-Gaussian fluctuations, abrupt shocks, and regime changes. To learn under discontinuous dynamics, we introduce a structurally constrained training objective based on a strong-form discretization of the underlying SDE. To characterise intrinsic predictability, we employ phase-space reconstruction and maximal Lyapunov exponent estimation. These diagnostics are interpreted as finite-sample measures of trajectory divergence and effective instability in a stochastic system, rather than evidence of low-dimensional deterministic chaos—a distinction motivated by well-documented limitations of chaos testing in financial data. Experiments on multiple West African currency pairs demonstrate competitive short-horizon forecasting performance relative to econometric and neural baselines while providing a principled framework for analysing predictability degradation under heavy-tailed stochastic dynamics. Across currencies and model classes, forecasting accuracy deteriorates beyond horizons comparable to the estimated Lyapunov time, suggesting that forecast degradation reflects intrinsic dynamical instability rather than model-specific limitations. The results support the view that reliable exchange-rate prediction is fundamentally a short-horizon problem and illustrate how stochastic dynamical modelling and predictability diagnostics can be combined to characterise forecasting limits in heavy-tailed financial systems. Full article

Accurate detection and reliable grasping of small bolts are essential for intelligent manufacturing and automated assembly. However, this remains a challenge due to the small size, slender geometry, and metallic reflective surfaces of bolts. In this paper, we propose a vision-guided robotic bolt handling framework that integrates lightweight object detection, optimization-oriented grasp execution, and collision-aware trajectory planning. The lightweight YOLOv8n-BoltLite detector, improved with E-C2f, LCA, SA-PAN, and WD-IoU loss, enhances localization accuracy and feature representation for small and slender bolts. A robotic grasping framework is designed to transform detection results into executable robotic actions through 3D pose estimation, mid-shank grasp point generation, and optimization-oriented execution formulation. Additionally, a five-segment trajectory planning strategy ensures safe and efficient robot motion. Experimental results show that YOLOv8n-BoltLite achieves a five-run average mAP of 99.64 ± 0.05% with 198 FPS, and 3.02 M parameters. On an additional challenging external test set involving illumination variation, clutter, partial occlusion, reflection, and clustered bolts, the proposed detector achieves 94.62 ± 0.18%, outperforming recent lightweight detectors under the same training protocol. Robotic experiments involving 1000 controlled grasping trials and 300 multi-target grasping attempts demonstrate a controlled-condition success rate of 97.0% and improved target-selection reliability in multi-bolt scenes. These results suggest that the proposed framework offers a practical and efficient solution for automated bolt handling in intelligent manufacturing environments. Full article

Background: Near-infrared spectroscopy (NIRS)-based wearable devices offer non-invasive, continuous monitoring of muscle oxygenation, providing direct microvascular and metabolic information that complements indirect indices of intensity such as heart rate and accelerometry. Their clinical applicability in chronic non-communicable diseases (NCDs) remains under active development. Methods: A structured narrative review was conducted in PubMed, Scopus, Web of Science, and IEEE Xplore (January 2010–January 2026) using pre-specified search strings combining NIRS, muscle oxygenation, SmO₂, StO₂, wearable, exercise intensity, ventilatory/lactate threshold, and individual chronic disease terms. Eligible studies addressed technical validation of wearable NIRS, NIRS-derived exercise intensity estimation, clinical applications in NCDs, or rehabilitation implementation. Evidence was synthesized thematically; quality of validation studies was appraised against AMSTAR-2-informed, COSMIN-informed, or Cochrane RoB-2 criteria. Results: Wearable continuous-wave NIRS shows acceptable concurrent validity with frequency-domain laboratory systems (r = 0.79; range 0.69–0.88; ±8% SmO₂ agreement in 95% of measurements) and good test–retest reliability for moderate-to-severe domains (ICC 0.72–0.91). NIRS-derived breakpoints align more reliably with the second ventilatory/lactate threshold (ICC = 0.80) than with the first (ICC = 0.53), constraining its use for prescribing lower-intensity domains. In chronic obstructive pulmonary disease, peripheral arterial disease, chronic respiratory failure and selected cardiovascular conditions, wearable NIRS detects disease-specific patterns of muscle deoxygenation and post-exercise reoxygenation that track responses to rehabilitation. Conclusions: Current evidence supports wearable NIRS as a complementary, intensity-aware monitoring tool—particularly for delineating the heavy/severe-intensity boundary and detecting peripheral metabolic limitations—rather than as a stand-alone replacement for ventilatory or lactate thresholds. Because much of the evidence derives from small, single-sex or athlete-only cohorts, these findings should be regarded as a promising basis requiring further validation in broader NCD populations. Implementation in NCDs requires standardized placement and calibration protocols, sex- and body composition-stratified reference values, motion-artifact mitigation, and adequately powered longitudinal trials in clinical populations. Full article

Heavy-duty industrial robots (HIRs) are essential for high-payload operations in the automotive, aerospace, and nuclear industries. However, existing reviews are often limited to specific domains or control methods. This paper provides a concise review of recent advances in HIRs from two perspectives: structural innovation and intelligent control. The review shows that structural design is evolving toward lightweight, robust, and maintainable architectures, while control strategies are increasingly shifting from conventional PID methods to adaptive, robust, and learning-based approaches to handle high inertia, nonlinear dynamics, and uncertainty. Representative applications, including friction stir welding and nuclear operations, are also summarized. Based on the reviewed literature, we identify several key challenges for future research, including structure–control co-design, energy-aware motion planning, robust autonomy in hazardous environments, safe human–robot collaboration, digital-twin-enabled lifecycle optimization, and interpretable fault diagnosis. These findings outline the research agenda for the next generation of HIRs. Full article

Extreme weather conditions impose significant challenges on distribution network inspection because UAV flight safety, energy consumption, vehicle mobility, and task coverage are strongly coupled under wind disturbances. To improve inspection efficiency and operational robustness, this paper proposes a weather-aware asynchronous vehicle–UAV cooperative scheduling method based on bi-level MODDPG–NSGA-II optimization. First, a dynamic wind field model and a wind-sensitive UAV energy model are established to describe the effects of background wind, vertical wind shear, and local gust disturbances on UAV motion and state-of-charge evolution. Then, an asynchronous vehicle–UAV collaboration mechanism is developed, allowing the vehicle to move toward downstream parking sites after UAV deployment while UAVs perform inspection and cross-site recovery under rendezvous and energy safety constraints. On this basis, a bi-level optimization framework is constructed, in which NSGA-II searches global coordination parameters and MODDPG learns adaptive multi-UAV scheduling policies in continuous decision spaces. Controlled wind-factor experiments show that, with the task scale fixed at 52 inspection tasks, the proposed method maintains 100% task coverage under 0–10 m/s wind conditions. As the reference wind speed increases from 0 m/s to 10 m/s, the mission completion time increases from 40.97 min to 70.24 min, while the minimum residual SOC decreases from 50.32% to 13.82%, which remains above the predefined safety threshold. Repeated stochastic trials and statistical significance analysis further indicate that the proposed method achieves shorter mission time and more stable task coverage than representative baselines under the same experimental conditions. The scope of this study is simulation-level validation; real-world flight tests and hardware-in-the-loop verification will be further investigated in future work. Full article

Vision-and-Language Navigation in continuous environments (VLN-CE) requires embodied agents to ground natural language instructions into reliable long-horizon motion decisions under partial observability. Despite their strong semantic understanding and reasoning abilities, Multimodal Large Language Model (LVLM) struggle when directly applied to VLN, as they lack explicit spatial grounding, embodied memory, and awareness of geometric and reachability constraints, leading to perceptual misalignment and cascading decision errors in complex scenes. To address these limitations, we propose STAMP, a Spatial-Temporal Anchored Motion Planning framework for zero-shot VLN-CE, which systematically bridges the gap between pretrained world knowledge and embodied navigation. STAMP adopts a hierarchical design that decouples high-level semantic reasoning from low-level motion execution, enabling a frozen LVLM to operate over a structured, navigation-oriented abstraction. Its core novelty lies in a multimodal spatial-temporal anchoring mechanism that explicitly encodes instruction-relevant landmarks, action semantics, depth-aware geometry, and historical navigation context, together with an explicit Chain-of-Navigation reasoning process that constrains decision-making to navigation-critical cues. Furthermore, STAMP incrementally constructs an online, backtracking-enabled topological map, supporting robust planning under uncertainty. Extensive experiments demonstrate the effectiveness of the proposed STAMP framework, achieving performance comparable to state-of-the-art zero-shot methods on VLN-CE benchmarks and in real-world settings. Full article

This review provides a comprehensive synthesis of robotic fruit harvesting systems, with a particular focus on the system-level integration of perception, manipulation, and fruit detachment within autonomous harvesting environments. Recent advances in machine vision, deep learning, sensor fusion, robotic end-effectors, grasping strategies, and motion planning are critically analyzed alongside cutting, pulling, and vibration-based detachment mechanisms under unstructured orchard conditions. Beyond component-level analysis, this review emphasizes the critical role of perception–action coupling and highlights key system integration challenges, including localization errors, perception-to-action latency, and environmental variability, which continue to limit reliable field deployment. In addition, orchard and pre-harvest-related factors such as canopy structure, fruit distribution, and detachment force variability are examined in relation to their direct impact on system performance, robustness, and harvesting efficiency. Furthermore, the review extends toward system-level considerations by incorporating performance evaluation metrics, economic feasibility, and scalability constraints, which are essential for transitioning robotic harvesting systems from experimental prototypes to commercially viable solutions, including practical field deployment in distributed and multi-robot harvesting systems. Emerging technologies, including artificial intelligence, advanced sensing, digital agriculture, and energy-aware system design, are discussed as key enablers for achieving adaptive, data-driven, and scalable autonomous harvesting. The novelty of this work lies in proposing an integrated framework that explicitly links perception, manipulation, and detachment with orchard-level constraints and deployment requirements, thereby bridging the gap between algorithmic advancements and real-world implementation of autonomous fruit harvesting systems. Full article

Traditional visual SLAM systems often suffer from localization drift in dynamic environments due to interference from moving objects. Although semantic segmentation and depth-based masking methods have improved performance, they may still suffer from boundary under-segmentation and missed detections due to truncation of dynamic objects. To address these challenges, we propose a cascaded framework, DMSG-SLAM, a cascaded visual SLAM system that fuses Depth-Mask, Semantic information and Geometry constraints for dynamic environments. A lightweight object detection network, combined with depth consistency, is first employed to generate instance-like masks for preliminary dynamic feature removal. Then, a rotation-aware local epipolar geometric filtering mechanism is introduced to suppress residual features near object boundaries and mitigate perceptual blind spots caused by occlusion or truncation. Within potential dynamic regions, the epipolar threshold is adaptively switched according to the estimated inter-frame rotation to provide a more conservative filtering effect under challenging motion conditions. In addition, a TSDF-based dense volumetric map is incorporated to reconstruct more consistent surfaces. Experiments on highly dynamic sequences from the TUM RGB-D dataset indicate that DMSG-SLAM achieves competitive accuracy in dynamic environments, with localization performance improving by up to 90% compared to ORB-SLAM2. Full article