Search Results (209)

Ultrasound examination for developmental dysplasia of the hip (DDH) in infants is highly dependent on operator experience, leading to inconsistent imaging quality and poor reproducibility between sonographers. This study proposes an autonomous robotic ultrasound system to improve the standardization and automation of hip ultrasound examinations. The system consists of a robotic arm, a six-axis force/torque sensor, an RGB-D camera and an ultrasound probe, integrating multiple functions including contact force control, visual localization, deep-learning-based segmentation and ultrasound image screening. To ensure stability and safety during scanning, an admittance-based hybrid force/position control strategy is adopted to achieve constant contact force control. For Graf standard plane acquisition, a stage-wise search strategy is designed, in which the search space is progressively narrowed through femoral head searching and multi-angle scanning. The optimal Graf standard plane is then automatically selected by combining image segmentation with a scoring mechanism. A customized hip phantom was used for validation. Experimental results show that the Dice coefficient for femoral head segmentation reaches 0.872, while the average Dice coefficient for multi-structure segmentation reaches 0.866. In 30 autonomous scanning trials, the success rate of Graf standard plane acquisition is 90.0%. Meanwhile, the system can maintain the contact force stably within the target range during scanning, validating the effectiveness of the force control strategy. These results indicate that the proposed robotic system, image recognition algorithm and visual servo control strategy exhibit favorable safety and feasibility, providing an innovative solution for automated infant hip ultrasound examination of DDH. Full article

Contact-rich manufacturing processes, such as surface cleaning, deburring, and polishing, require precise force regulation and complex trajectory tracking that are challenging to automate using conventional robot programming methods. Learning from Demonstration (LfD) offers a powerful alternative to transfer these expert skills from human operators to robotic systems. The objective of this study is to systematically map academic publications addressing LfD applications in robotic deburring and polishing between 2016 and 2026, classify the algorithmic structures, sensory modalities, and control configurations employed, and identify key industrial integration challenges. In accordance with the PRISMA 2020 guidelines, a systematic search was conducted across Scopus, Web of Science, IEEE Xplore, and Google Scholar databases. Out of the 288 initially retrieved records, duplicate removal and a two-stage screening process (Title/Abstract review, followed by full-text review) resulted in a final corpus of 24 primary studies included for qualitative synthesis. The included studies were classified into five algorithmic clusters: Dynamic Movement Primitives (DMPs) and variants (9 out of 24 studies, 38%), probabilistic and statistical models (8 out of 24 studies, 33%), deep learning and generative AI architectures (4 out of 24 studies, 17%), autonomous dynamical systems (2 out of 24 studies, 8%), and direct impedance control (1 out of 24 studies, 4%). Force/torque sensing remains the dominant modality; it was utilized exclusively in 71%—17 out of 24—of studies and in 87.5% of studies as any configuration (either as a sole modality or in multimodal setups). However, recent years have documented a trend toward multimodal perception and generative action policies (e.g., Diffusion Policies). The findings suggest that while LfD offers potential cost-reduction and flexibility benefits for small- and medium-sized enterprises (SMEs), technical barriers, such as the sim-to-real transfer gap, high-frequency impact dynamics in deburring, and the autonomous identification of local non-polishing areas (LNP areas), continue to limit widespread industrial deployment. Full article

This scoping review synthesizes 35 studies on sensor technologies and artificial intelligence for fruit detection, classification, and quality assessment, contrasting Latin American and international research traditions. The analysis suggests notable differences in technological approaches between the included Latin American and international studies: Latin American research tends to emphasize in developing accessible, practical solutions using classical computer vision and low-cost hardware, while international studies more frequently employ through deep learning architectures, multi-modal sensing, and complete robotic automation systems. Across the included studies, relatively limited attention was given to AI-assisted decision support for agricultural practitioners, insufficient consideration of inclusivity, and the scarce integration of environmental sustainability into intelligent sensing system design. The review identifies that only 8 of 35 studies originate from Latin America, suggesting an uneven geographical distribution of the available evidence. The included studies generally reported high accuracy values, yet these findings must be interpreted with caution given the reliance on curated datasets that may not represent real-world variability. The reviewed evidence suggests that future research may benefit not from one approach dominating the other, but from a thoughtful integration of complementary strategies, including knowledge transfer, edge computing democratization, and human-centered design. Overall, this review suggests that the ultimate goal extends beyond accuracy metrics to the transformation of agricultural practices that enhance food security, economic development, and environmental sustainability across the global agricultural landscape. It is important to note that this work does not propose or validate a new fruit detection algorithm but rather synthesizes and critically evaluates existing scientific evidence regarding sensor technologies and artificial intelligence applied to fruit detection and quality assessment. Full article

Pipe welding automation requires accurate weld seam extraction and reliable robotic weld path generation under complex geometric conditions. Existing vision-based approaches often rely on expensive laser sensing systems, multi-view sensing, or continuous seam tracking, resulting in increased hardware cost and system complexity. To address these limitations, this study proposes a deep learning-based offline robotic welding framework that generates a three-dimensional welding path from a single top-view Red–Green–Blue and Depth (RGB-D) image acquired prior to welding. The proposed framework integrates weld seam detection, semantic segmentation, morphology-based post-processing, RGB-D image alignment, coordinate transformation, and polynomial-based trajectory refinement into a unified pipeline for robotic weld path generation. A custom pipe welding dataset consisting of 1476 annotated images collected from representative industrial pipe materials with varying diameters was constructed to evaluate the proposed framework. The experimental results demonstrate that the proposed Region of Interest (ROI)-guided weld seam extraction pipeline improves the U-Net segmentation performance from 0.735 to 0.791 mean Intersection over Union (mIoU), while the detection model achieves a Recall of 0.988 and an mean Average Precision at an Intersection over Union threshold of 0.5 (${\mathrm{mAP}}_{50}$) of 0.995. Furthermore, polynomial-based trajectory refinement reduces the three-dimensional positional root mean square error (RMSE) to 0.333 mm, enabling continuous robotic welding over the entire visible weld seam without additional path modification. These results demonstrate that the proposed framework provides a practical and cost-effective solution for offline robotic weld seam extraction and weld path generation, while establishing a promising foundation for future extension toward online robotic welding through real-time weld seam tracking and adaptive trajectory correction. Full article

Brinjal (Solanum melongena L.) is an important vegetable crop worldwide, but its cultivation faces challenges from pests, diseases, and variable environmental conditions that negatively affect quality and yield. Accurate fruit detection in natural field conditions is essential for yield estimation and perception module of automated harvesting, but existing deep learning techniques often require substantial computational support, restricting their deployment on edge devices. This study addresses this gap by evaluating the Faster Objects, More Objects (FOMO) model—a lightweight architecture for resource-constrained platforms—for brinjal detection under diverse field conditions. A dataset of 1500 images was captured under varying illumination and growth stages, annotated using a bounding box-based approach, and used to train FOMO models with 25, 50, and 100 epochs via transfer learning. Post-training quantization to INT8 format was applied to assess improvements in computational efficiency. The Float32 model achieved a precision of 0.827, recall of 0.915, and F1-score of 0.869 at 100 epochs. The INT8-quantized model maintained comparable accuracy (precision 0.829, recall 0.908, F1-score 0.866) while reducing model size by 63.33% (from 0.30 MB to 0.11 MB), inference time by 62.02% (from 65.3 ms to 24.8 ms), and RAM usage by 73.02% (from 887.2 KB to 239.4 KB). These results demonstrate that FOMO combined with INT8 quantization provides an efficient, accurate solution for real-time brinjal detection on edge platforms, supporting the advancement of precision agriculture through intelligent crop monitoring and serving as a perception module for future robotic harvesting systems. Full article

The automation of fruit harvesting has become an important research topic in precision agriculture due to increasing labor shortages, rising production costs, and the need for improved harvesting efficiency. Among horticultural crops, strawberries present particular challenges for robotic harvesting because of their variability in size, shape, ripeness, and frequent occlusions caused by leaves and surrounding fruit. The objective of this work is to demonstrate the feasibility of a reproducible perception-to-manipulation framework for robotic strawberry harvesting based on commercially available hardware and established computer vision techniques, rather than to propose a novel object detection algorithm. The proposed system integrates a YOLOv3-based (You Only Look Once) object detector, monocular vision for fruit localization, and a Universal Robots UR5e collaborative manipulator. Strawberry coordinates estimated from monocular images are transformed into the robot reference frame and transmitted through the XML-RPC (Extensible Markup Language-Remote Procedure Call) protocol, enabling robot positioning. The system was experimentally validated in a controlled indoor environment under different artificial illumination conditions. The YOLOv3 detector achieved a ${\mathrm{mAP}}_{0.5:0.95}$ of 37.4%, a precision of 84.2%, a recall of 76.1%, and a latency of 6.5 ms per image (153.8 FPS). The experiments also demonstrated reliable communication between the perception and robotic manipulation modules, enabling the robotic arm to reach the estimated strawberry positions. The proposed framework provides a practical and low-cost solution for integrating deep-learning-based perception with robotic manipulation and establishes a solid basis for future work on localization accuracy, automated grasping, harvesting efficiency, and deployment in real agricultural environments. Full article

Path tracking control and algorithm portability for agricultural robots serve as the core technological foundation for achieving precision and automation in farming operations, playing a critical role in ensuring food security and enhancing production efficiency. This paper systematically reviews recent technological advancements in the field. It first elucidates the fundamental theories and technical components of path tracking control, providing detailed analyses of the characteristics and limitations of traditional methods such as Proportional-Integral-Derivative (PID) control, model predictive control (MPC), sliding-mode control (SMC), and the Stanley algorithm. Subsequently, it focuses on innovations in intelligent technologies, exploring the integration trends of adaptive control and intelligent learning algorithms, with particular emphasis on the combined applications of reinforcement learning, deep learning, and intelligent control methodologies. The paper clarifies the significance of algorithm portability and summarizes the current applications and performance differences among various algorithms. The study concludes that traditional methods demonstrate stability and reliability in structured scenarios, while advanced intelligent approaches exhibit stronger adaptability in complex environments, albeit facing challenges such as data dependency and real-time deployment requirements. Future technological developments will prioritize deep integration of multiple technologies and the unified achievement of both safety and real-time performance. Full article

Artificial intelligence (AI) is reshaping the field of diagnostic radiology; however, its applications in interventional radiology and pediatric interventional radiology (PIR) remain limited despite clear clinical needs and the rich multimodal data environment characteristic of pediatric procedural care. In this narrative review, I summarize the current state of AI technologies relevant to PIR and outline future perspectives for their clinical integration. Peer-reviewed literature and position statements identified through MEDLINE/PubMed, Embase, Scopus, and major society publications up to the first quarter of 2026 are synthesized, focusing on AI applications across the PIR care pathway, including dose-sparing image acquisition and reconstruction, automated image interpretation and computer-aided diagnosis, data-driven procedural planning and navigation, and post-procedural risk prediction and monitoring. After briefly introducing core machine learning and deep learning concepts, pediatric-specific challenges are discussed, including radiation sensitivity, growth-related anatomical variability, regulatory constraints, and the scarcity of large, annotated datasets, as well as existing and emerging applications along the PIR care pathway: AI-assisted dose reduction and image reconstruction, automated image interpretation, segmentation, and computer-aided diagnosis; data-driven procedural planning, including three-dimensional modelling, augmented reality, AI-enabled/AI-adjacent robotics, and AI-directed procedural navigation; and post-procedural risk prediction and outcome monitoring. Finally, emerging paradigms, including explainable AI, federated learning, and multimodal integration, are highlighted, and research priorities, collaborative frameworks, and governance principles required to ensure safe, equitable, and effective AI deployment in PIR are outlined. In doing so, this review delineates the current evidence gaps and priority directions for clinically meaningful AI adoption in PIR. Although AI has the potential to improve patient care, it has not yet been specifically designed, validated, or deployed in children. Existing work demonstrates feasibility across the PIR workflow, but most tools remain weakly linked to pediatric clinical endpoints. Full article

Fouling on ship hulls increases hydrodynamic drag, fuel consumption, and emissions. This, in turn, necessitates the development of efficient methods for side cleaning and inspection. This work focuses on the application of image-based classification to assess the cleanliness of the surface of the hull in robotic cleaning systems, with respect to the ISO 8501-4 standard. Due to limited data availability, transfer learning techniques using pre-trained convolutional neural networks (ResNet50, EfficientNetB0 and MobileNetV2) were used. Both end-to-end models and hybrid approaches that combine deep feature extraction with XGBoost (version 3.2.0) classification were evaluated. Experiments were carried out on binary classification (cleaned vs. uncleaned surfaces) and multi-class classification of cleanliness levels (WA1, WA2, WA2.5). The results show that transfer learning enables effective recognition of cleaning status, achieving high performance for binary classification despite a small dataset. However, multi-class classification remains challenging due to subtle differences between classes and data limitations. The proposed approach supports automated visual inspection of underwater robotic platforms and represents a step toward objective standards-based assessment of hull cleaning processes. Full article

The objective of this study was to design, fabricate, and test an automated inter-row robotic system for the precision management of Palmer amaranth (Amaranthus palmeri) in cotton. A Farm-ng robotic platform with custom-designed weed pulling and cutting attachments was used to achieve weed control. The pulling system consisted of two counter-rotating rollers with a frictional cover to uproot weeds, followed by a cutting operation to shred the weeds into smaller pieces, preventing regrowth. A deep learning model, YOLOv11s, was used for weed identification, while point cloud data from a stereo camera was used to estimate weed height in real-time for dynamic adjustment of the puller height. The system was evaluated at three forward speeds (0.06, 0.15, and 0.25 m/s), two roller speeds (107 and 161 RPM), and three attachment configurations (puller-only, cutter-only, and combined). The combined configuration consistently outperformed individual operations, achieving 80% control at 0.15 m/s and a roller speed of 161 RPM. Optimal performance was observed when the angular puller velocity was 15–25 times the forward speed of the rover. This approach demonstrates the potential of integrating mechanical weed removal with real-time computer vision to improve weed management and reduce labor requirements. Full article

Industrial robots are indispensable equipment in automated production lines and play a crucial role in advancing the development of intelligent manufacturing. Bearings are key components within robot joints. To ensure the precise execution of operational tasks and to prevent potential safety accidents in a timely manner, it is essential to perform fault diagnosis on the bearings within robot joints. However, fault diagnosis methods based on deep learning typically require a large amount of fault measurement data, which can be challenging to obtain due to various constraints. To address the issue of insufficient data, this paper proposes a fault diagnosis method based on the integration of digital twin technology and MTF-ResTLN. First, a digital twin model of the industrial robot is established, and fault excitations are injected into different nodes of the twin model to generate fault data under various node conditions. The measured data are then combined with the simulated fault data to form a training dataset. Furthermore, a novel classifier is developed by integrating the Markov Transition Field with a Residual Transfer Learning Network. It achieves cross-domain fault diagnosis and enhances the capability of fault diagnosis. Full article

Artificial Intelligence (AI) is revolutionizing Construction Management (CM) through automation, predictive analytics, and real-time decision-making throughout the project lifecycle.This study aims to provide a comprehensive and structured synthesis of AI models and their applications in CM. This paper presents a systematic review of 191 peer-reviewed articles published between 2020 and 2025, aiming to integrate the current state of AI implementation in CM, focusing on AI methods and models and their applications in CM. Compared to previous reviews that take these factors individually or focus narrowly on specific techniques, this study offers a comprehensive taxonomy that systematically maps AI techniques against CM functions and integration platforms. The results reveal that AI applications are primarily concentrated in risk and safety management, decision support, and monitoring and control, while domains such as legal analytics, robotics, and cybersecurity remain underexplored. Furthermore, Computer Vision (CV) and Deep Learning (DL) dominate tasks such as safety monitoring and defect detection, whereas Machine Learning (ML) and optimization algorithms are widely applied in cost estimation and scheduling. It also addresses developments rarely covered in construction research, including Generative AI (Gen-AI), Explainable AI (XAI), and transformer models, presenting a strategic framework for the widespread adoption of AI in the construction environment. This study contributes a structured taxonomy that systematically links AI models with CM functions and enabling technologies, providing a comprehensive synthesis of emerging trends and research gaps. Full article

Blueberry production has rapidly expanded over the past decade, accompanied by growing demand for efficient and accurate methods to monitor the flowering and fruiting phases of blueberry development, which has a direct impact on yield potential. Accurate determination of blueberry phenology enables growers to make data-driven decisions on freeze protection applications and harvest windows. In addition, objective phenology data of blueberry mapping populations will provide high-quality phenotype data for the discovery of genetic mechanisms regulating blueberry flowering and fruiting times. Traditional approaches, such as manual counting and visual ratings, are labor-intensive and subjective in capturing variation across genotypes. Recent progress in computer vision and deep learning has enabled automated flower detection, but most existing studies on blueberries remain restricted to narrow flowering windows or close-up images, limiting their application at the bush level and across the seasonal development. In this study, we developed BerryFlowerNet, a customized YOLO-based model to detect and count blueberry flower clusters from bud to green fruit stages. A comprehensive dataset was collected on three dates using a field phenotyping robot, covering five flowering stages. The integration of CFNet, a custom module fusing shallow spatial features, and PIoU loss improved the detection performance. Additionally, the Slicing Aided Hyper Inference algorithm was employed to address small-object detection in bush-level images. Experimental results demonstrated that BerryFlowerNet outperformed the baseline YOLO model and three additional detectors, achieving an average mAP0.5 of 0.644 across five independent training runs. The model achieved an accuracy of 0.88 when predicting blueberry flowering stages, indicating its effectiveness and accuracy. Additionally, the results of the bush-level image analysis showed the capability of the model to capture genotype-level differences in flowering dynamics. Overall, this approach offers new opportunities for growers and breeders to determine blueberry phenological development that is critical for optimizing on-farm management strategies and advancing precision phenotyping to facilitate the development of climate-resilient blueberries. Full article

Peripheral nerve blocks can effectively reduce the use of general anesthesia and opioids in situations where robust pain management is critical, such as severe extremity trauma and hip, femur, and knee surgeries. Despite these benefits, nerve blocks are underutilized due to the high skill required to accurately insert a needle and safely deliver local anesthetic. To overcome this challenge, ultrasound image guidance enabled by artificial intelligence (AI) offers a semi-automated solution for regional anesthesia delivery by non-specialists. As a first step towards realizing an integrated platform for AI-guided nerve blocks, the main objective of this study is to develop and characterize deep learning algorithms to interpret anatomical landmarks on ultrasound images in real time and identify aimpoints for needle placement. Our AI system was trained on over 55,000 images from 20 porcine models and demonstrated an average area under the precision–recall curve of 0.92 (SD = 0.03) for in vivo landmark detection in the femoral nerve region. In prospective live animal testing, aimpoint identification had a 98.3% success rate with an average time of 40.5 s (SD = 33.5). Future work will focus on integrated testing with handheld robotics towards a more accessible method for delivering regional anesthesia in settings from point of injury to medical transport to hospitals. Full article

Winter pruning is a key management practice in viticulture that directly affects vine architecture, yield balance, and grape quality. At the same time, it is a highly labor-intensive operation, and the selective identification of appropriate cutting locations remains one of the main challenges limiting the automation of pruning in vineyards. Advances in machine vision provide new opportunities to support the development of robotic pruning systems. The objective of this study was to develop and evaluate a vision-based method for estimating grapevine pruning points and cutting lines using instance segmentation outputs generated by YOLO models. A dataset of 1500 RGB images of dormant grapevines was collected under field conditions in the Nobilis vineyard located in southeastern Poland. Two annotation strategies were implemented to define pruning regions. YOLO-based instance segmentation models were trained and evaluated for detecting cutting-related structures. Based on the predicted segmentation masks, a geometry-based method termed PCAcutSeg-V was developed to estimate class-dependent cutting points and cutting lines using principal component analysis applied to object contours. The results indicate that YOLOv8 and YOLO11 architectures achieved the highest segmentation performance among the evaluated models. The simplified annotation strategy provided more stable geometric inputs for the PCAcutSeg-V method, enabling more reliable estimation of cutting points and cutting lines compared with the extended annotation approach. When combined with the PCAcutSeg-V method, the proposed perception–geometry pipeline achieved high effectiveness in pruning decision estimation. The method was further implemented in a real-time processing pipeline using an RGB camera and an edge computing platform, where it maintained performance consistent with the results obtained from offline image analysis. These findings demonstrate that combining deep learning-based instance segmentation with deterministic geometric reasoning enables accurate and interpretable estimation of grapevine pruning locations and provides a promising foundation for future autonomous pruning systems. Full article