Search Results (724)

Background: Esophageal cancer, the seventh most common malignancy globally, requires esophagectomy for curative treatment. However, esophagectomy is associated with high postoperative morbidity and mortality, highlighting the need for minimally invasive approaches. Robotic-assisted surgery has emerged as a promising alternative to traditional open and minimally invasive esophagectomy (MIE), offering potential benefits in improving clinical and oncological outcomes. This review aims to assess the postoperative morbidity and outcomes of robotic surgery. Methods: A comprehensive review of the current literature was conducted, focusing on studies evaluating the role of robotic-assisted surgery in esophagectomy. Data were synthesized on the clinical outcomes, including postoperative complications, survival rates, and recovery time, as well as technological advancements in robotic surgery platforms. Studies comparing robotic-assisted esophagectomy with traditional approaches were analyzed to determine the potential advantages of robotic systems in improving surgical precision and patient outcomes. Results: Robotic-assisted esophagectomy (RAMIE) has shown significant improvements in clinical outcomes compared to open surgery and MIE, including reduced postoperative pain, less blood loss, and faster recovery. RAMIE offers enhanced thoracic access, with fewer complications than thoracotomy. The RACE technique has improved patient recovery and reduced morbidity. Fluorescence-guided technologies, including near-infrared fluorescence (NIRF), have proven valuable for sentinel node biopsy, lymphatic mapping, and angiography, helping identify critical structures and minimizing complications like anastomotic leakage and chylothorax. Despite these benefits, challenges such as the high cost of robotic systems and limited long-term data hinder broader adoption. Hybrid approaches, combining robotic and open techniques, remain common in clinical practice. Conclusions: Robotic-assisted esophagectomy offers promising advantages, including enhanced precision, reduced complications, and faster recovery, but challenges related to cost, accessibility, and evidence gaps must be addressed. The hybrid approach remains a valuable option in select clinical scenarios. Continued research, including large-scale randomized controlled trials, is necessary to further establish the role of robotic surgery as the standard treatment for resectable esophageal cancer. Full article

Soft arms, characterized by their compliance and adaptability, have gained significant attention in applications ranging from industrial automation to biomedical fields. Modeling these systems presents unique challenges due to their high degrees of freedom, nonlinear behavior, and complex material properties. This review provides a comprehensive overview of three primary modeling approaches: numerical methods, analytical techniques, and data-driven models. Numerical methods, including finite element analysis and multi-body dynamics, offer precise but computationally expensive solutions for simulating soft arm behaviors. Analytical models, rooted in continuum mechanics and simplified assumptions, provide insights into the fundamental principles while balancing computational efficiency. Data-driven approaches, leveraging machine learning and artificial intelligence, open new avenues for adaptive and real-time modeling by bypassing explicit physical formulations. The strengths, limitations, and application scenarios of each approach are systematically analyzed, and future directions for integrating these methodologies are discussed. This review aims to guide researchers in selecting and developing effective modeling strategies for advancing the field of soft robotic arm design and control. Full article

The application of robotic arms in the industrial field is continuously becoming greater and greater. The impact force generated by a robotic arm in a gripping operation leads to vibration and wear. To address this problem, this paper proposes a trajectory planning method based on the improved Slime Mould Algorithm. An interpolation curve under the joint coordinate system is constructed by using seven non-uniform B-spline functions, with time and impact force as the optimization objectives and angular velocity, angular acceleration, and angular acceleration as the constraints. The original algorithm introduces Bernoulli chaotic mapping to increase the diversity of the population, adaptively adjusts the feedback factor, improves the crossover operator to accelerate the global convergence, and combines the original algorithm with an improved artificial bee colony search strategy guided by the global optimal solution, adding a quadratic interpolation method to increase the diversity of the population and to accelerate the global convergence speed. Combined with the improved artificial swarm search strategy guided by the global optimal solution, the quadratic interpolation method is added to enhance the local utilization ability. The simulation and real-machine experimental results show that the improved algorithm shortens the movement time of the robotic arm, reduces the joint impacts, minimizes the vibration and wear, and prolongs the service life of the robotic arm. Full article

Simultaneous localization and mapping (SLAM) is one of the key technologies for mobile robots to achieve autonomous driving, and the lidar SLAM algorithm is the mainstream research scheme. Firstly, this paper introduces the overall framework of lidar SLAM, elaborates on the functions of front-end scan matching, loop closure detection, back-end optimization, and map building module, and summarizes the algorithms used. Then, the classical representative SLAM algorithms are described and compared from three aspects: pure lidar SLAM algorithm, multi-sensor fusion SLAM algorithm, and deep learning lidar SLAM algorithm. Finally, the challenges faced by the lidar SLAM algorithm in practical use are discussed. The development trend of the lidar SLAM algorithm is prospected from five dimensions: lightweight, multi-sensor fusion, combination of new sensors, multi-robot collaboration, and deep learning. This paper can provide a brief guide for novices entering the field of SLAM and provide a comprehensive reference for experienced researchers and engineers to explore new research directions. Full article

The combination of vision and robotic grinding technology provides robots with “visual perception” capabilities that enable them to accurately locate the area to be ground and perform the grinding tasks efficiently. Based on the rough grinding requirements for wheel hub burrs proposed by a casting company, this paper investigates the application of a vision-guided grinding robot in treating burrs on wheel hub castings. First, through vision system calibration, the conversion from pixel coordinate system to robot base coordinate system is implemented, thus ensuring that the subsequently extracted burr point coordinates can be correctly mapped to the robot’s operational coordinate system. Next, the images of the burrs on wheel hub castings are collected and processed. All the burr points are extracted by applying image algorithms. In order to improve grinding accuracy, a height error compensation model is established to adjust the coordinates of the 2D-pixel points; the coordinate error after compensation was reduced by 58.33%. Subsequently, the compensated burr point trajectories are optimized by utilizing an intelligent optimization algorithm to generate the shortest grinding path. Through experimental analysis of the relationship between spindle speed and surface roughness, a grinding trajectory simulation model is constructed, and the simulation results are integrated into the robot system. Finally, actual wheel hub burr grinding experiments are performed to validate the effectiveness and practicality of the proposed solution. Full article

Robot visual servoing for grasping has long been challenging to execute in complex visual environments because of issues with efficient feature extraction. This paper proposes a novel visual servoing grasping approach based on the Deep Visual Servoing Feature Network (DVSFN) to tackle this issue. The approach enables feasible to extract scale-invariant point features and target bounding boxes in real time by building an effective single-stage multi-dimensional feature extractor. The DVSFN is then integrated into a Levenberg–Marquardt–based image visual servoing (LM-IBVS) controller. The above creates a mapping link between the robot’s joint space and image features. The robot is then guided in positioning and grabbing by converting the difference between the expected and present features into the corresponding robot joint velocities. Experimental results demonstrate that the proposed method achieves a mean average precision (mAP) of 0.80 and 0.87 for detecting target bounding boxes and point features, respectively, in scenarios with significant lighting variations and occlusions. Under low-light and partial occlusion conditions, the method achieves an average grasping success rate approximately 80%. Full article

Digital twin (DT) technology has become a cornerstone in the simulation and analysis of real-world systems, offering unparalleled insights into the lifecycle management of physical assets. By providing a real-time synchronized replica of the physical entity, DTs enable predictive maintenance, performance optimization, and lifecycle extension, which are pivotal for industries aiming for digital transformation. This paper presents a comprehensive comparative study of DT development of a robotic arm using two prominent simulation platforms: Unity and Gazebo. Unity, with its roots in the gaming industry, offers robust real-time rendering and a user-friendly interface, making it a versatile choice for various industries. Gazebo, traditionally used in robotics, provides detailed physics simulations and sensor data emulation, which is ideal for precise engineering applications. We explored the performance of both platforms in creating accurate and dynamic digital replicas. Through qualitative and quantitative analyses, this study evaluates each platform’s strengths and limitations. The study assesses these platforms across key performance metrics such as accuracy, latency, graphic quality, and integration with the Robot Operating System (ROS). The DTs were developed using a consistent physical setup and communication layer to ensure fair comparisons. The results indicate that Unity performed better in terms of accurately mimicking the robotic arm with lower latency, making it ideal for applications requiring high-fidelity visualizations and real-time responsiveness. However, Gazebo excels in its ease of ROS integration and cost-effectiveness, making it a suitable choice for smaller robotics and automation projects. This study conducts an empirical comparison of these platforms in terms of their performance in creating DTs of robotic arms which is not readily available. This paper aims to guide developers and organizations in selecting the appropriate platform for their DT initiatives, ensuring efficient resource utilization and optimal outcomes. Full article

The increasing demand for autonomous mobile robots in complex environments calls for efficient path-planning algorithms. Bio-inspired algorithms effectively address intricate optimization challenges, but their computational cost increases with the number of particles, which is great when implementing algorithms of high accuracy. To address such topics, this paper explores the application of the leader-based bat algorithm (LBBA), an enhancement of the traditional bat algorithm (BA). By dynamically incorporating robot orientation as a guiding factor in swarm distribution, LBBA improves mobile robot localization. A digital compass provides precise orientation feedback, promoting better particle distribution, thus reducing computational overhead. Experiments were conducted using a mobile robot in controlled environments containing obstacles distributed in diverse configurations. Comparative studies with leading algorithms, such as Manta Ray Foraging Optimization (MRFO) and Black Widow Optimization (BWO), highlighted the proposed algorithm’s ability to achieve greater path accuracy and faster convergence, even when using fewer particles. The algorithm consistently demonstrated robustness in bypassing local minima, a notable limitation of conventional bio-inspired approaches. Therefore, the proposed algorithm is a promising solution for real-time localization in resource-constrained environments, enhancing the accuracy and efficiency in the guidance of mobile robots, thus highlighting its potential for broader adoption in mobile robotics. Full article

Light scattering and attenuation in water degrade underwater images with low visibility and color distortion, which often interfere with the high-level visual tasks of underwater autonomous robots. Most existing deep learning methods for underwater image enhancement only supervise the final output of network and ignore the promotion effect of the intermediate results on the final feature representation. These supervision methods affect the feature representation ability, network efficiency, and ability. In this paper, we present a novel idea of multiple-stage supervision to guide the network to learn useful features correctly and progressively. With this idea, we propose a pixel-wise Progressive Guided Network (PGN) for underwater image enhancement to take advantage of the network’s intermediate results and promote the final enhancement effect. The Pixel-Wise Attention Module is designed by introducing supervision in each stage to progressively promote the representation ability of the features and the recovered image quality. The experimental results on several datasets demonstrate that our method outperforms recent state-of-the-art underwater image enhancement methods. Full article

Objectives: Accurate target definition, treatment planning and delivery increases local tumor control for radiotherapy by minimizing collateral damage. To achieve this goal for uveal melanoma (UM), tantalum fiducial markers (TFMs) were previously introduced in proton and photon beam radiotherapy. However, TFMs cause pronounced scattering effects in imaging that make the delineation of small tumors difficult. The aim of this study was to evaluate silicone fiducial markers (SFMs) for the guiding of stereotactic radiosurgery (SRS) for UM. Methods: In this retrospective interventional pilot case series, three patients with small UMs 3 mm or less in tumor thickness and ≤10 mm in largest basal diameter received silicone fiducial markers. The fiducial markers were punched out (3 mm) from conventional silicone encircling bands for buckle surgery. The markers were sutured onto the sclera at the tumor margins according to the use of TFMs. MRI and CT images were used for the localization of the tumor and the markers before robotic-guided SRS. Results: The silicone fiducial markers were punched out easily from the original band, better to handle than TFMs and easy to suture onto the sclera. They could be visualized in both MRI and CT, but were more visible in CT. In the absence of scattering effects, both the markers and thus the tumor boundaries could be clearly delineated. Conclusions: This is the first report that introduces fiducial markers intraoperatively shaped from conventional silicone encircling bands usually used for retinal detachment surgery. The SFMs allow more accurate tumor delineation, resulting in the more precise planning and administration of SRS when compared to TFMs. This simple modification has a major impact on a well-known treatment approach. Full article

Snake robots, inspired by the biology of snakes, are bionic robots with multiple degrees of freedom and strong robustness. These robots represent a current area of significant research interest within the field of robotics. Snake robots have a wide range of applications in many fields, advancing the integration of bionics, robotics, and cybernetics, while playing a crucial role in performing survey and rescue missions. This survey presents the latest technological advancements in modeling, motion control, and guidance laws for planar snake robots, and provides a unified perspective based on the existing results. To achieve target-tracking control of robots in complex environments, we present a feasible approach that integrates guided vector field technology and transforms the target-tracking and obstacle avoidance problem into a reference angle tracking issue. Finally, this paper analyzes and summarizes the development process and key technologies of snake robot control and provides an outlook on future development trends. Full article

Aiming at the problems of a six-degree-of-freedom robotic arm in a three-dimensional multi-obstacle space, such as low sampling efficiency and path search failure, an improved fast extended random tree (RRT*) algorithm for robotic arm path planning method (abbreviated as HP-APF-RRT*) is proposed. The algorithm generates multiple candidate points per iteration, selecting a sampling point probabilistically based on heuristic values, thereby optimizing sampling efficiency and reducing unnecessary nodes. To mitigate increased search times in obstacle-dense areas, an artificial potential field (APF) approach is integrated, establishing gravitational and repulsive fields to guide sampling points around obstacles toward the target. This method enhances path search in complex environments, yielding near-optimal paths. Furthermore, the path is simplified using the triangle inequality, and redundant intermediate nodes are utilized to further refine the path. Finally, the simulation experiment of the improved HP-APF-RRT* is executed on Matlab R2022b and ROS, and the physical experiment is performed on the NZ500-500 robotic arm. The effectiveness and superiority of the improved algorithm are determined by comparing it with the existing algorithms. Full article

Background: Vestibular symptoms can severely affect patients with vestibular schwannomas (VSs). Studies assessing vestibular symptoms beyond clinical routine assessment in patients with VS treated by stereotactic radiosurgery (SRS) are scarce. Therefore, we employed the standardized questionnaire Dizziness Handicap Inventory (DHI) to systematically evaluate vestibular symptoms prior to and after SRS. Methods: For this retrospective single center study, we included patients who received Cyberknife^® SRS for newly diagnosed unilateral VS between 2012 and 2022, and who had a minimum of two follow-up (FU) visits. Besides clinical assessment, the presence and severeness of vestibular symptoms before and after treatment was recorded by using the DHI. Overall DHI symptom scores (1–100) were classified into four grades (0 = “none”, 1 = “mild”, 2 = “moderate” and 3 = “severe”). The results were correlated with tumor-, patient-, and treatment-related characteristics. Results: We analyzed 128 patients with a median age of 60 years (range: 20–82) and a median FU of 36 months (range: 11–106 months). The median tumor volume was 0.99 cm³ (range: 0.04–7.1 cm³). A median marginal dose of 13 Gy (range: 12–14 Gy) was administered. The crude rate of local tumor control was 99.2%. The mean DHI total score at last follow-up (LFU, 25.5 ± 24.7; range 0–92) was significantly lower than before SRS (29.4 ± 25.3; range:0–92, p = 0.026), which was reflected in a higher proportion of patients with DHI grade “none” and a lower proportion of patients with DHI grade “severe” at LFU. Chi-square tests showed a significant correlation of the DHI grades (DHI 0–1 vs. DHI 2–3) with the absence or presence of vestibular symptoms both before SRS (p < 0.001, CI 95%) and at LFU (p = 0.038). Conclusions: The DHI is a feasible and valid instrument for measuring vestibular symptoms after SRS. In addition, the DHI enables the quantification of symptoms and can therefore serve as an important tool for outcome assessment after SRS of VS. In the present cohort, DHI scores improved significantly during FU. Full article

Transferring knowledge learned from standard GelSight sensors to other visuotactile sensors is appealing for reducing data collection and annotation. However, such cross-sensor transfer is challenging due to the differences between sensors in internal light sources, imaging effects, and elastomer properties. By understanding the data collected from each type of visuotactile sensors as domains, we propose a few-sample-driven style-to-content unsupervised domain adaptation method to reduce cross-sensor domain gaps. We first propose a Global and Local Aggregation Bottleneck (GLAB) layer to compress features extracted by an encoder, enabling the extraction of features containing key information and facilitating unlabeled few-sample-driven learning. We introduce a Fourier-style transformation (FST) module and a prototype-constrained learning loss to promote global conditional domain-adversarial adaptation, bridging style-level gaps. We also propose a high-confidence guided teacher–student network, utilizing a self-distillation mechanism to further reduce content-level gaps between the two domains. Experiments on three cross-sensor domain adaptation and real-world robotic cross-sensor shape recognition tasks demonstrate that our method outperforms state-of-the-art approaches, particularly achieving 89.8% accuracy on the DIGIT recognition dataset. Full article

As we progress towards Industry 5.0, technological advancements are converging; this movement is realised by the increasing collaboration between humans and intelligent digital platforms and further enabled by the interactive visualisation modes provided by Metaverse technology. This research examines the practical applications and limitations of Metaverse technology providing insights into the transformative possibilities it offers for the manufacturing sector. Specifically, the research was guided by the core objective to trace the evolution of Metaverse technology within manufacturing. This study provides a comprehensive and state-of-the-art analysis of the adoption and impact of Metaverse technologies in the manufacturing sector. While previous research has explored aspects of Industry 4.0 and digital transformation, this study specifically focuses on human-centric manufacturing (human-in-the-loop) applications of Metaverse technology, including augmented reality, virtual reality, digital twins, and cyber-physical robotic systems. Findings from the systematic literature review indicate that Metaverse technologies, primarily augmented reality and virtual reality, have evolved into powerful tools in manufacturing. They are widely adopted across sectors in the industry, transforming processes such as product design, quality control, and maintenance. Augmented reality and virtual reality offer intuitive ways to visualise data and interact with digital twins, bridging the gap between physical and virtual realms in manufacturing. A roadmap and scenarios for the introduction of Metaverse technology in manufacturing are provided with suggested adoption timespans. Furthermore, the systematic literature review identified barriers hindering the wider adoption of Metaverse technology in manufacturing. Full article