Search Results (829)

Extended Reality (XR) technologies have matured into powerful tools for training in high-stakes domains, from emergency response to search and rescue. Yet current systems often struggle to balance real-time AI-driven personalisation with the need for human oversight and calibrated trust. This article synthesizes the programmatic contributions of a multi-study doctoral project to advance a design-and-evaluation framework for trustworthy adaptive XR training. Across six studies, we explored (i) recommender-driven scenario adaptation based on multimodal performance and physiological signals, (ii) persuasive dashboards for trainers, (iii) architectures for AI-supported XR training in medical mass-casualty contexts, (iv) theoretical and practical integration of Human-in-the-Loop (HITL) supervision, (v) user trust and over-reliance in the face of misleading AI suggestions, and (vi) the role of interaction modality in shaping workload, explainability, and trust in human–robot collaboration. Together, these investigations show how adaptive policies, transparent explanation, and adjustable autonomy can be orchestrated into a single adaptation loop that maintains trainee engagement, improves learning outcomes, and preserves trainer agency. We conclude with design guidelines and a research agenda for extending trustworthy XR training into safety-critical environments. Full article

Segmentation of tomato fruits under complex lighting conditions remains technically challenging, especially in low illumination or overexposure, where RGB-only methods often suffer from blurred boundaries and missed small or occluded instances, and simple multimodal fusion cannot fully exploit complementary cues. To address these gaps, we propose YOLO-MSRF, a lightweight RGB–NIR multimodal segmentation and refinement framework for robust tomato perception in facility agriculture. Firstly, we propose a dual-branch multimodal backbone, introduce Cross-Modality Difference Complement Fusion (C-MDCF) for difference-based complementary RGB–NIR fusion, and design C2f-DCB to reduce computation while strengthening feature extraction. Furthermore, we develop a cross-scale attention fusion network and introduce the proposed MS-CPAM to jointly model multi-scale channel and position cues, strengthening fine-grained detail representation and spatial context aggregation for small and occluded tomatoes. Finally, we design the Multi-Scale Fusion and Semantic Refinement Network, MSF-SRNet, which combines the Scale-Concatenate Fusion Module (Scale-Concat) fusion with SDI-based cross-layer detail injection to progressively align and refine multi-scale features, improving representation quality and segmentation accuracy. Extensive experiments show that YOLO-MSRF achieves substantial gains under weak and low-light conditions, where RGB-only models are most prone to boundary degradation and missed instances, and it still delivers consistent improvements on the mixed four-light validation set, increasing $mA{P}_{0.5}$ by 2.3 points, $mA{P}_{0.5–0.95}$ by 2.4 points, and mIoU by 3.60 points while maintaining real-time inference at 105.07 FPS. The proposed system further supports counting, size estimation, and maturity analysis of harvestable tomatoes, and can be integrated with depth sensing and yield estimation to enable real-time yield prediction in practical greenhouse operations. Full article

Background and Clinical Significance: Tramadol-associated acute angle-closure crisis is rare and has been reported only once previously following subcutaneous administration. Acute angle closure may occur in anatomically predisposed individuals in the setting of perioperative physiological stress, with medications acting as contributory factors. Case Presentation: A 38-year-old woman developed a bilateral acute angle-closure crisis shortly after initiating oral tramadol for postoperative pain relief following an uncomplicated robotic-assisted laparoscopic hysterectomy. Within 24 h, she experienced headache, nausea, vomiting, periocular pain, and blurred vision. Ophthalmic examination revealed markedly elevated intraocular pressure (45 mmHg OD, 39 mmHg OS), corneal epithelial edema, mid-dilated pupils, and completely closed angles on gonioscopy. Prompt intraocular pressure–lowering therapy followed by bilateral Nd:YAG laser peripheral iridotomy resulted in full anatomical and functional recovery, with visual acuity returning to baseline within 48 h. Conclusions: In this case, extreme anatomical susceptibility due to significant hyperopia and very short axial lengths likely played a dominant role, with perioperative physiological factors contributing to pupillary dilation. Oral tramadol may have acted as a permissive factor lowering the threshold for angle closure rather than as a sole causative agent. Awareness of this potential association is important to facilitate early ophthalmic referral and prevent unnecessary diagnostic evaluations. Full article

Cable-driven parallel robots (CDPRs) are increasingly favored in rehabilitation, medical devices, and material transportation due to their flexible structure and large transmission distance. The CDPRs with a highly modular and flexible structure are usually easy to be quickly reorganized. It is important to study the dimension and shape optimization of the basis and moving platforms for rapidly reconstructing a high-performance CDPR. The influence of each parameter of CDPRs’ dimension and shape on performance is mutually coupled. Therefore, obtaining the global optimal result by simply superimposing each optimum parameter is usually difficult. To this end, the concepts of a constant stiffness space (CSS) and a cable-tension-constrained workspace (CTCW) and their calculation methods are introduced, and the CDPRs’ dimension and shape are optimized with the maximum CSS and CTCW volume as the optimization indicators. First, the response surface optimization model between CDPRs’ performance and multi-objective optimization parameters is established, taking into account the coupling relationship of each CDPR optimization parameter and the effect on performance, and it is solved by using the Latin hypercube design method. Then, the effect of CDPRs’ dimension and shape on performance is analyzed by using the response surface optimization model, and the CDPRs’ optimization dimensions are provided. Full article

Various recurring medical events encourage innovative patient well-being through connected health strategies based on an elegant digital environment that prioritizes safety, comfort, and beneficial outcomes for both patients and medical staff. This narrative review article aims to investigate and highlight the potential of advanced, reliable, high-precision, and secure medical observation and intervention missions. These involve a smart digital environment integrating smart materials combined with smart digital monitoring. These medical implications concern robotic surgery and drug delivery through image-assisted implantation, as well as wearable observation and assistive tools. The former requires high-precision motion and positioning strategies, while the latter enables sensing, diagnosis, monitoring, and central task assistance. Both advocate minimally invasive or noninvasive procedures and precise supervision through autonomously controlled processes with staff participation. The article analyzes the requirements and evolution of medical interventions, robotic actuation technologies for positioning actuated and self-moving instances, monitoring of image-assisted robotic procedures using digital twins and augmented digital tools, and wearable medical detection and assistance devices. A discussion including future research perspectives and conclusions complete the article. The different themes addressed in the proposed paper, although self-sufficient, are supported by examples of the literature, allowing a deeper understanding. Full article

Pneumatic artificial muscles (PAMs) are inherently compliant and relatively safe. They are widely used in applications where human beings and robots interact closely, such as service robots or medical robots. However, PAMs are constrained by bulky pumps and valve control systems, limiting their mobility, portability, and practical applications. In this research, a novel type of artificial muscle, namely Twisting Tube Artificial Muscle (TTAM), is presented. In a TTAM design, fluid (pressurized air in this research) is contained inside an elastic tube (constrained by a braiding). By twisting the tube from one end, the fluid inside the twisted part will be extruded to the untwisted part, resulting in a pressure increase inside the untwisted part. Both the twisted and untwisted parts will thus contract. Modeling and experimental characterization of the TTAM are conducted. In an experimental test at 100 kPa initial air pressure, after a 6π twisting angle, the internal pressure of a prototype TTAM is increased to 219 kPa, and the largest contraction force of the TTAM was up to 200 N. A novel antagonistic robotic joint actuated by two TTAMs is developed as a sample application. Full article

Object identification (OI) is widely used in fields like autonomous driving, security, robotics, environmental monitoring, and medical diagnostics. OI using infrared (IR) images provides high visibility in low light for all-day operation compared to visible light. However, the low contrast often causes OI failure in complex scenes with similar target and background temperatures. Therefore, there is a stringent requirement to enhance IR image contrast for accurate OI, and it is ideal to develop a fully automatic process for identifying objects in IR images under any lighting condition, especially in photon-deficient conditions. Here, we demonstrate for the first time a highly accurate automatic IR OI process based on the combination of polarization IR imaging and artificial intelligence (AI) vision (Yolov7), which can quickly identify objects with a high discrimination confidence level (DCL, up to 0.96). In addition, we demonstrate that it is possible to achieve accurate IR OI in complex environments, such as photon-deficient, foggy conditions, and opaque-covered objects with a high DCL. Finally, through training the model, we can identify any object. In this paper, we use a UAV as an example to conduct experiments, further expanding the capabilities of this method. Therefore, our method enables broad OI applications with high all-day performance. Full article

Digital telecommunications have become the backbone of modern healthcare, transforming how patients and professionals interact, share information, and deliver treatment. The integration of telecommunications with medicine, biomedical engineering and health services has enabled rapid growth in telemedicine, remote patient monitoring, wearable biomedical devices, and data-driven clinical decision-making. Emerging technologies such as artificial intelligence, big data analytics, virtual and augmented reality and robotic tele-surgery are further expanding the scope of digital health. This review provides a comprehensive overview of the role of telecommunications in medicine and biomedical engineering. We classify key applications, highlight enabling technologies and critically examine the challenges regarding interoperability, data security, latency, and cost. Finally, we discuss future directions, including 5G/6G networks, edge computing, and privacy-preserving medical AI, emphasizing the need for reliable and equitable access to telecommunications-enabled healthcare worldwide. Full article

We presented a biomimetic approach to designing robot-to-human handover of objects in a collaborative assembly task. We developed a human–robot hybrid cell where a human and a robot collaborated with each other to perform the assembly operations of a product in a flexible manufacturing setup. Firstly, we investigated human psychology and biomechanics (kinetics and kinematics) for human-to-robot handover of an object in the human–robot collaborative set-up in three separate experimental conditions: (i) human possessed high trust in the robot, (ii) human possessed moderate trust in the robot, and (iii) human possessed low trust in the robot. The results showed that human psychology was significantly impacted by human trust in the robot, which also impacted the biomechanics of human-to-robot handover, i.e., human hand movement slowed down, the angle between human hand and robot arm increased (formed a braced handover configuration), and human grip forces increased if human trust in the robot decreased, and vice versa. Secondly, being inspired by those empirical results related to human psychology and biomechanics, we proposed a novel robot-to-human object handover mechanism (strategy). According to the novel handover mechanism, the robot varied its handover configurations and motions through kinematic redundancy with the aim of reducing potential impulse forces on the human body through the object during the handover when robot trust in the human was low. We implemented the proposed robot-to-human handover mechanism in the human–robot collaborative assembly task in the hybrid cell. The experimental evaluation results showed significant improvements in human–robot interaction (HRI) in terms of transparency, naturalness, engagement, cooperation, cognitive workload, and human trust in the robot, and in overall performance in terms of handover safety, handover success rate, and assembly efficiency. The results can help design and develop human–robot handover mechanisms for human–robot collaborative tasks in various applications such as industrial manufacturing and manipulation, medical surgery, warehouse, transport, logistics, construction, machine shops, goods delivery, etc. Full article

Background/Objectives: Socially assistive robots effectively support elderly care when they incorporate personalization, person-centered principles, rich interactions, and careful role setting with psychosocial alignment. Hyodol, a socially assistive robot designed for elderly people, embodies a grandchild’s persona, emulating the grandparent–grandchild relationship. Based on the behavioral activation principles and a human-centered approach, this robot continuously supports users’ emotional well-being, health management, and daily routines. Methods: The current study evaluated Hyodol’s impact on depressive symptoms and other quality of life factors among older adults living in medically underserved areas. A total of 278 participants were assessed for depressive symptoms, loneliness, medication adherence, and user acceptance. Results: After six months of use, participants showed significant reductions in overall depressive symptoms, with a 45% decrease in the proportion of individuals at high risk of depression. Significant improvements were also observed in loneliness and medication adherence. Participants reported high levels of user acceptance and satisfaction, exceeding 70% of the total score. Participants who engaged more frequently in free chat with Hyodol showed greater improvements in depressive symptoms. Conclusions: These results highlight Hyodol’s potential as a promising tool for enhancing mental healthcare and overall well-being in this population. This at-home mental-healthcare framework can complement primary care and, if its effects are confirmed in controlled trials, could contribute to reducing healthcare burden and preventing the onset and escalation of depressive symptoms. Full article

Background: Management of lateral pelvic lymph node (LPLN) metastasis in advanced lower rectal cancer has historically exemplified a fundamental East–West divide. In Japan, the Japanese Society for Cancer of the Colon and Rectum (JSCCR) considers LPLN metastasis a regional manifestation requiring lateral pelvic lymph node dissection (LPLND). In contrast, Western practice has long approached LPLN disease as systemic, prioritizing neoadjuvant chemoradiotherapy (nCRT) followed by total mesorectal excision (TME) without additional lateral clearance. Recent Advances: Evidence generated from the JCOG0212 trial and subsequent multicenter cohorts has firmly demonstrated that LPLND markedly reduces lateral local recurrence, particularly in patients with radiologically enlarged nodes. These findings have contributed to a paradigm shift: the 2025 European Society for Medical Oncology (ESMO) Guidelines now endorse selective LPLND for suspicious nodes following neoadjuvant therapy, indicating an emerging convergence between Eastern surgical philosophy and Western multimodal treatment strategies. Surgical Innovation: Robotic surgery has transformed the technical execution of LPLND. Its stable, high-definition three-dimensional visualization, wristed instruments, and enhanced precision enable meticulous dissection across four anatomically defined planes: the medial plane (uretero-hypogastric fascia), intermediate plane (vesico-hypogastric fascia), lateral plane (pelvic sidewall), and dorsal plane (pelvic floor and lumbosacral trunk/sacral plexus). These features facilitate consistent nerve-sparing surgery, reduce blood loss, and improve postoperative urinary and sexual function compared with conventional laparoscopy or open approaches. Robotic LPLND therefore represents a contemporary synthesis of Eastern surgical precision and Western evidence-based multimodal therapy—offering an integrated pathway toward optimized oncologic control and enhanced functional outcomes. Full article

Objectives: To evaluate clinical and biochemical outcomes of robotic-assisted laparoscopic adrenalectomy in patients with primary aldosteronism (PA) due to small aldosterone-producing adenomas, with emphasis on blood pressure (BP) control, antihypertensive medication burden, hormonal normalization, and safety. Methods: We prospectively enrolled PA patients (aldosterone >10 ng/dL, renin <2 μU/mL) undergoing robotic adrenalectomy by a single surgeon. Exclusions included suspected pheochromocytoma, other adrenal pathologies, or malignancy. Outcomes were classified per PASO criteria at 6 months: complete success (BP <140/90 mmHg without medications + normalized aldosterone (<10 ng/dL) and renin (>2 μU/mL)), partial success (improvement in BP control with reduced medication and/or partial biochemical improvement), and failure (persistent hypertension and abnormal hormone levels). Results: From 2019 to present, 18 patients (median age 53 years; 13 male) with a median adenoma size of 15 mm (IQR 10–19.8) underwent robotic adrenalectomy (12 left, 6 right). Three (16.7%) with bilateral imaging findings had adrenal vein sampling to confirm unilateral disease. At 6 months, complete clinical success was achieved in 10 (55.5%) patients, partial success in 7 (38.9%), and failure in 1 (5.6%). Biochemically, 12 achieved complete normalization, 3 achieved partial improvement, and 3 did not complete testing. Median operative time was 110 min (IQR 100–120); median hospital stay was 3 days (IQR 3–4). No intra- or postoperative complications, transfusions, infections, or readmissions occurred. Conclusions: Robotic adrenalectomy for small aldosterone-producing adenomas in PA is safe, with high rates of BP normalization and hormonal remission and significantly reduced antihypertensive medication burden. Full article

Self-powered sensors, leveraging their integrated energy harvesting–signal sensing capability, effectively overcome the bottlenecks of traditional sensors, including reliance on external power resources, high maintenance costs, and challenges in large-scale distributed deployment. As a result, they have become a major research focus in fields such as flexible electronics, smart healthcare, and human–machine interaction. This paper reviews the core technical paths of six major types of self-powered sensors developed in recent years, with particular emphasis on the working principles and innovative material applications associated with frictional charge transfer and electrostatic induction, pyroelectric polarization dynamics, hydrovoltaic interfacial streaming potentials, piezoelectric constitutive behavior, battery integration mechanism, and photovoltaic effect. By comparing representative achievements in fields closely related to self-powered sensors, it summarizes breakthroughs in key performance indicators such as sensitivity, detection range, response speed, cyclic stability, self-powering methods, and energy conversion efficiency. The applications discussed herein mainly cover several critical domains, including wearable medical and health monitoring systems, intelligent robotics and human–machine interaction, biomedical and implantable devices, as well as safety and ecological supervision. Finally, the current challenges facing self-powered sensors are outlined and future development directions are proposed, providing a reference for the technological iteration and industrial application of self-powered sensors. Full article

Inflammatory bowel disease (IBD) includes Crohn’s disease (CD) and ulcerative colitis (UC). The accurate classification of IBD from colonoscopy images is critical for diagnosis and treatment. However, the lack of labeled data poses a major challenge for developing deep learning-based IBD classification approaches. Recently, pseudo-labeling-based semi-supervised learning methods offer a promising solution in leveraging both labeled and unlabeled data to improve classification performance. Nevertheless, due to significant intra-class variability and the subtle inter-class differences in IBD colonoscopy images, pseudo-labels are often inaccurate, which results in confirmation bias and suboptimal performance. To address this challenge, a Subclass-Aware Contrastive Semi-Supervised Learning method, referred to as SACSSL, is proposed for accurate IBD classification by integrating a subclass-aware contrastive module into a pseudo-labeling-based semi-supervised framework, e.g., FixMatch. Specifically, unlabeled samples are first partitioned into confident and uncertain samples according to the confidence of pseudo-labels. An instance-level contrastive loss is then applied to uncertain samples, aiming to mitigate confirmation bias. Furthermore, intra-class heterogeneity is captured by introducing a set of prototypes for each subclass and assigning confident samples to these prototypes to form fine-grained subclasses, and supervised contrastive loss is applied to promote intra-subclass clustering, thereby enhancing inter-class separability while preserving intra-class diversity. Our method is evaluated on two datasets, i.e., an in-house collected Daping dataset for IBD classification and a publicly available LIMUC dataset for UC severity grading. On both datasets, our method achieves state-of-the-art performance under the semi-supervised setting. Specifically, with only 20% labeled data, the proposed method reaches an overall accuracy of 93.2% and an F1-score of 80.1% on the Daping dataset, which is close to the fully supervised upper bound (94.0% accuracy and 80.8% F1-score), and it achieves an overall accuracy of 76.4% and an F1-score of 68.9% on the LIMUC dataset. Comprehensive experimental results demonstrate the effectiveness of our method for semi-supervised colonoscopy image classification. Full article

Background and Objectives: Robot-assisted procedures represent a significant advancement in minimally invasive liver resection techniques. Nonetheless, the introduction of a novel surgical technique in a new environment necessitates meticulous planning and a gradual, stepwise approach. This study describes the adoption of a robotic surgical platform for liver resection at a high-volume tertiary care center. Materials and Methods: We retrospectively analyzed data that had been prospectively collected from fifty robot-assisted liver resections. Descriptive statistics, including frequencies, percentages, means/medians, and standard deviations, were employed for description and summary. Results: The median operative duration was 166 min (range: 85–400 min), with an average intraoperative blood loss of 200 mL (range: 50–1000 milliliters). Intraoperative or postoperative blood transfusion was required in 8% of patients. Conversion to open resection was necessary in one patient (2%). The mean duration of hospitalization was 5 days (range: 3–20 days), with a 30-day readmission rate of 6% and no mortality within 90 days. Postoperative complications classified as Clavien-Dindo grade 3 or higher were observed in five patients (10%). The mean tumor size varied according to pathology: 58.5 mm (range: 30–120 mm) in the hepatocellular carcinoma group; 27.4 mm (range: 10–32 mm) in the secondary malignancy group; and 42.6 mm (range: 24–60 mm) in the intrahepatic cholangiocarcinoma group. The median number of lymph nodes harvested during lymphadenectomy (IHHCA/GBCA) was 5.4, ranging from 1 to 11. The R0 resection rate for malignant tumors was 88.2% (of 30/34). Conclusions: This study validates the safe integration of robot-assisted surgery into liver disease treatment, supported by our initial experience. Despite its technical advantages, robotic-assisted liver surgery remains complex and demanding. Structured robotic training within established programs, meticulous patient selection, and a stepwise implementation approach are critical during the early phases to optimize the outcomes. Full article