Search Results (278)

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 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

With the development of the low-altitude economy, low-altitude intelligent agents such as delivery robots, courier drones, and outdoor cleaning robots are gradually moving towards widespread application. One of the core challenges faced by such systems is localization and mapping in complex scenarios characterized by satellite signal denial and unknown environmental prior information. To address this requirement, this paper proposes ESKF-g2o-SLAM, a stereo visual-inertial SLAM system that integrates an ESKF (Error-State Kalman Filter)-based visual-inertial odometry front-end with an ORB-feature-based g2o graph optimization back-end in a cascaded, loosely coupled manner. The proposed method was evaluated on 11 sequences of the EuRoC dataset and compared with state-of-the-art approaches including ORB-SLAM2 (stereo), MSCKF-VIO, OKVIS, and VINS-Fusion (stereo). Ablation studies show marginal improvements on selected sequences and suggest potential robustness advantages under more challenging visual conditions. Experimental results show that our method achieves competitive accuracy in terms of both Absolute Trajectory Error (ATE) and Relative Pose Error (RPE), exhibiting good robustness and stability. Full article

Achieving precise docking, reliable locking and damage-free emergency unlocking under complex ocean current conditions remains a key challenge for deep-water multi-way quick connectors (MQCs). This study proposes a novel MQC prototype characterised by a tiered tolerance guidance mechanism, an innovative L-shaped spatial helical cam locking system, and a real-time visual attitude indicator. Using Ansys 2023 R2 and its tools, the safe operating limits were determined through explicit non-linear finite element collision analysis. The results demonstrate that, under a controlled docking speed of 10 mm/s, the hierarchical guidance mechanism successfully accommodated extreme initial misalignments (25 mm lateral offset, 5° horizontal rotation and 15° axial rotation), whilst keeping the peak collision stress within the elastic limit. Furthermore, the L-shaped locking guide was analysed using a fifth-order polynomial motion law and a macro-micro elastoplastic Hertzian contact mechanics model, effectively eliminating rigid-flexible impact forces. Under extreme separation loads of 10,000 psi, the maximum equivalent plastic strain at the base of the locking shaft was strictly controlled at 0.00926. This is well below the failure threshold of 0.0865 specified by ASME, providing a substantial safety margin and completely preventing local yielding. Crucially, the emergency release strategy based on precision locating pins was validated through full-scale prototype testing. Destructive tests conducted under simulated severe jamming conditions demonstrated clean, damage-free disengagement under shear torques ranging from 2100 Nm to 2200 Nm. This threshold ensures that accidental triggering will absolutely not occur during routine operations (1400 Nm) and establishes a safe underwater robotic (ROV) operating speed of ≤4 r/min. This study provides a robust theoretical framework and empirical data for the future design of yield-resistant subsea connectors and safe emergency recovery. Full article

Wet cleaning robots have seen a boost in popularity in recent years, with notable impact on their technical features and portfolio of functionalities. To improve cleaning results as well as to create unique selling points, robot manufacturers introduce and expand on new wet cleaning concepts such as self-regenerating roller mops, close-to-wall operation and floor sterilisation. This paper takes a narrative approach to provide an overview of the development of wet cleaning robots for household usage in the span of the last four years (2022–2025). During this period, significant advancements have been made to increase the wet cleaning potential in household robots, both wet & dry cleaning units and dedicated wet cleaning models. The review focuses on developments that directly enhance wet cleaning performance (e.g., mop kinematics, regeneration and hygiene functions) and deliberately excludes advances that are not specific to wet cleaning (e.g., battery chemistry or generic navigation). As part of the review process, the findings are checked against the current landscape of technical standardisation. Thus, the paper identifies normative gaps which have opened due to the absence of international technical standards for wet cleaning robots. It advises on filling these gaps by establishing and updating testing guidelines to address new developments. Full article

Solar energy is emerging as a cornerstone of the global renewable energy transition, with projections indicating that photovoltaics (PV) could contribute up to 90% of electricity generation by 2050. However, environmental factors, particularly dust deposition, pose a significant challenge to the long-term performance and efficiency of PV systems. Dust accumulation varies widely across different geographic regions, influenced by climate, land use, humidity, and pollution. Arid and semi-arid areas experience the highest deposition rates, while tropical and temperate regions are affected by seasonal rainfall and urban pollutants. This review comprehensively examines the impact of dust on PV performance, highlighting factors such as surface roughness of PV module, panel tilt angle, seasonal variations, wind dynamics, and dust composition. Furthermore, the review assesses various dust mitigation strategies, including manual and water-based cleaning, robotic systems, hydrophobic coatings, and electrostatic methods. By synthesizing global studies and presenting a holistic view of dust effects, this paper provides critical insights into the impact of performance degradation with regional variation in PV, optimizing performance, maintenance, and effective dust mitigation strategies to ensure sustained energy yield and reliability in solar energy systems worldwide. Full article

The continuous and reliable monitoring of soil organic carbon and soil respiration is vital for sustainable agricultural and environmental management. However, current manual methods are labor-intensive and time-consuming. This work focuses on the development of a fully automated robotic platform for in situ measurement of Soil Organic Carbon (SOC) and Soil Respiration (${\mathbf{R}}_s$). The system consists of a four-wheeled mobile platform, equipped with a robotic arm, and custom sampling and measurement tools. The platform is designed with a protected central opening that houses an on-board laboratory, enabling automated surface cleaning, soil drilling, sample collection and homogenization, SOC spectroscopy analysis, and chamber-based soil respiration measurement. The platform is equipped with a high-force mechanical insertion mechanism capable of operating a range of tools designed for soil treatment and penetration. These tools include a soil surface scraper, a soil respiration chamber, and a soil drilling unit. The mobile robotic laboratory system enables the sequential deployment of these tools in any desired order, providing flexible and efficient in-field operation. Full article

Autonomous cleaning robots operating in semi-structured dynamic environments must execute task-oriented motions while safely interacting with surrounding agents. These agents include pedestrians, vehicles, and other robots. In such environments (e.g., interaction-rich campus environments), reliable self-decision-making requires anticipating the future motions of surrounding agents rather than relying solely on reactive obstacle avoidance. This paper presents a trajectory prediction-enabled self-decision-making framework for autonomous cleaning robots in campus environments. A learning-based multi-agent trajectory prediction model is trained offline using public benchmarks and real-world operational data to capture typical interaction patterns in corridor-following, edge-cleaning, and intersection scenarios. The predicted trajectories are then incorporated as forward-looking priors into the robot’s online decision-making and planning process, enabling prediction-aware yielding, detouring, and task continuation decisions. The proposed framework is evaluated using real-world data-driven scenario reconstruction on a high-fidelity simulation platform that incorporates realistic vehicle dynamics and heterogeneous traffic participants. This evaluation focuses on short-horizon prediction performance and its impact on downstream decision-making stability. The results show that integrating trajectory prediction into the decision-making loop leads to more stable motion behavior and fewer abrupt adjustments in interaction scenarios. Under short-term prediction horizons, the evaluation results show that the proposed model achieves ADERate and FDERate exceeding 90% under predefined error thresholds, while lane-change prediction accuracy remains around 79%. In addition, the robot maintains stable speed tracking with only minor fluctuations under medium-density traffic conditions. Full article

Net cleaning robots have been playing an increasingly important role in offshore aquaculture due to their efficiency and labor-saving capabilities. However, in practice, these robots are still entirely teleoperated and require constant, skilled human operation. The mesh intersection points, which serve as a structural feature of the nets, provide valuable visual cues for robot self-localization and net damage identification. Therefore, the detection and tracking of these points are crucial for developing autonomous net cleaning robots. To achieve intersection point detection, we propose NPUNet-lite, a lightweight model based on U-Net. This model significantly minimizes computational resources and model size while preserving high detection accuracy. For reliable point tracking, we develop the NlPTrack algorithm, which incorporates an iterative closest point-based association strategy to meet spatial constraints between points within a frame, and a cascaded association strategy to satisfy homographic and epipolar constraints across adjacent frames. We build a dataset from videos collected during a robotic cleaning task to train and evaluate our methods. The experimental results indicate that our segmentation network achieves comparable accuracy to advanced networks, yet with a substantial reduction in computational cost. Meanwhile, the tracking method successfully tracks the majority of intersection points across scenarios where the robot moves in different directions. Full article

This paper presents a finite-time uniformly ultimately bounded (FTUUB) cooperative control strategy based on a nonlinear disturbance observer (NDOB) for high-precision collaborative control of multi-hydraulic robotic arm systems operating under unknown disturbances and model uncertainties in confined scenarios such as coal silo cleaning. The proposed approach simplifies control design by lumping various uncertainties into a total disturbance, which is estimated and compensated in real time by the NDOB. Building upon this, a finite-time convergent sliding mode controller is developed, wherein the disturbance compensation is inherently embedded, ensuring that both position and velocity tracking errors converge to a small neighborhood of zero within a finite time. A master–slave distributed control architecture is adopted, with the agent communication topology characterized by graph theory. To mitigate the chattering inherent in traditional sliding mode control, a smooth hyperbolic tangent function is employed to construct the sliding surface. Rigorous Lyapunov stability analysis demonstrates that the closed-loop system achieves uniform ultimate boundedness within a finite time. Comprehensive simulation experiments, including a digital twin-based visualization in a virtual coal silo environment, validate the superior performance of the proposed method in terms of tracking accuracy, convergence speed, disturbance rejection, and control smoothness. Full article

To better address the operational requirements for emergency underwater ship maintenance, this study proposes the use of an underwater robotic arm instead of divers for cleaning submerged hull sections. Experimental analyses are conducted to validate the stability and feasibility of the constructed underwater robotic arm cleaning system. Initially, hydrodynamic analysis of the robotic arm was performed using the Morison equation. Through fluent dynamic simulations, the hydrodynamic moments on each robotic arm during cleaning operations were obtained, confirming that stress under typical seawater flow velocities remained within the rated limits. Subsequently, dynamic simulations were carried out to determine the joint driving torques in a fluid environment, quantify the influence of the hydrodynamic resistance on the joint torque, and verify the accuracy of the fluid dynamics model. Finally, motion control and underwater cleaning experiments were implemented on the system. Experimental results further corroborated the correctness of the fluid model and operational environment analysis, demonstrating the expected cleaning performance and providing both data and experimental support for practical underwater maintenance during long-distance ship voyages. Full article

Tunnel lighting cleaning is of significant practical importance for improving driving safety. To address the low operational efficiency of tunnel lighting cleaning tasks, a trajectory planning method based on the chaotic adaptive whale–particle swarm optimization (CAW-PSO) algorithm is proposed. Taking the SIASUN GCR16-2000 robotic arm as the research object, the trajectory is constructed using a 3-5-3 polynomial interpolation, with the objective of achieving time-optimal trajectory planning. In the CAW-PSO algorithm, a tent chaotic map is introduced to improve the quality of the population; a linearly decreasing inertia weight is designed to strike a balance between local and global search; dynamic learning factors are defined to strengthen the individual learning ability and global cognitive capability of particles; finally, the exploitation mechanism of the whale optimization algorithm is employed to avoid getting trapped in local optima and improve convergence accuracy. The simulation time is 3.661 s, a reduction of 69.94%. The experimental results yielded a mean relative error of 1.16%, indicating good agreement with the simulation results. The results of the simulation and experiment indicate that the CAW-PSO effectively reduces the motion time of the robotic arm, exhibiting superior applicability in trajectory planning for tunnel lighting cleaning robotic arms. Full article

Stain detection is crucial for robotic sweepers, enabling them to assess environmental hygiene and execute precise cleaning tasks. However, in complex indoor scenarios, highly accurate stain detection remains a significant challenge, as the visual features of stains are often obscured by ambient light, background textures, and specular reflections. Most existing deep learning methods rely predominantly on standard Red-Green-Blue (RGB) images, which lack sufficient discriminative features to robustly distinguish stains from complex backgrounds or accurately classify diverse contaminants. To address these limitations, we propose a deep learning stain detection framework integrated with a multispectral polarization optical system. First, to extract discriminative optical features, we design a lightweight multispectral polarization optical module tailored for integration into robotic sweepers. It captures rich spectral and polarization features while effectively suppressing specular reflections. Second, to enhance feature representation capabilities, we develop a multispectral polarization (MP)-based stain detector, named MP-stain-detector, which fuses spectral composition data with polarization texture features. Third, to support rigorous model training and evaluation, we construct a comprehensive dataset, the MP-Stain-dataset, collected in real-world home scenarios. Experiments on the MP-Stain-dataset demonstrate that our method improves the overall mean accuracy by 2.44%, and by 5.72% for the challenging light-colored liquid category compared to conventional approaches. Full article

This paper presents the development of Electrohouse, a 3D educational simulator used for illustrating the electricity consumption of a household in the presence of a photovoltaic (PV) system designed to teach users how to efficiently manage electrical equipment from an energy perspective. The paper addresses elements of energy system modeling, human–computer interaction and educational visualization. The application connects electricity consumption graphs with practical appliance controls, providing a comprehensive view of kilowatt-hour usage with an intuitive interface. The software offers two consumption scenarios, with one for 28 days and one for 30 days. Furthermore, the household displays the integration of a photovoltaic solar panel for direct energy production, with the system simulating an actual meter by deducting the generated current from the accumulated consumption. Relevant for sustainability, especially in the fields of energy education, the project incorporates the creation of a prototype of a night-time home surveillance robot designed for intruder detection and control. This study contributes to the global framework of Sustainable Development Goals (SDGs) adopted by the United Nations. The simulator supports SDG 7 (Affordable and Clean Energy) by promoting awareness of photovoltaic integration with household energy optimization and SDG 4 (Quality Education) by providing an interactive digital learning environment that improves energy literacy with sustainability-oriented skills. Full article

Background/Objectives: The Mitrofanoff appendicovesicostomy (MAV) is the gold standard for creating a continent catheterizable channel in children unable to perform clean intermittent catheterization (CIC) through the native urethra. Minimally invasive surgery has progressively replaced open techniques in pediatric urology, offering improved recovery and favorable cosmetic outcomes, and robotic-assisted Mitrofanoff has gained popularity in recent years. However, the high costs and limited availability of robotic systems create disparities in access to pediatric urologic reconstruction, particularly in low- and middle-income countries. In this context, the laparoscopic Mitrofanoff (MAV-L) and the laparoscopic-assisted Mitrofanoff (MAV-LA) represent practical, cost-effective alternatives, valuable in institutions without robotic platforms or in resource-limited settings. Recent evidence demonstrates that advanced laparoscopic approaches remain feasible even for complex urological procedures, supporting their continued relevance in the robotic era. Methods: We conducted a retrospective case series including seven male children (aged 9–12 years) who underwent MAV between 2018 and 2023. Peri-operative data included demographics, operative time, length of hospitalization, and complications. Functional and aesthetic outcomes were assessed during long-term follow-up. Statistical analysis accounted for the small sample size by using non-parametric tests where appropriate. Results: Three patients (43%) underwent MAV-L and four (57%) MAV-LA. Mean operative time appeared longer in MAV-L (273.3 ± 20.5 min) than in MAV-LA (203.8 ± 24.3 min; exploratory p = 0.019). Hospital stay was 9 ± 0.8 days vs. 7.5 ± 0.5 days (p = 0.026). During follow-up (43.3 ± 10.9 vs. 26.3 ± 5.4 months; p = 0.034), two complications occurred, both in the MAV-L group (stomal stenosis and channel leakage). All patients reported excellent continence, ease of catheterization, and high cosmetic satisfaction. Conclusions: Both laparoscopic and laparoscopic-assisted Mitrofanoff techniques are safe, feasible, and effective in children. Favorable cosmetic satisfaction was reported in the fully laparoscopic subgroup, based on subjective assessment. Importantly, these laparoscopic techniques are sustainable alternatives to robotic surgery, offering accessibility and high-quality reconstructive care even in centers with limited financial and technological resources. Full article

This study introduces a novel robust finite-time adaptive sliding mode control (FTSMC) strategy, emphasizing its contributions to the synchronized deployment of hydraulically actuated multi-arm systems in confined environments, such as coal bunker cleaning. Key innovations include the integration of adaptive sliding mode control with guaranteed finite-time convergence, a distributed leader–follower framework, and a graph-theoretical communication topology for localized interactions. Specifically, we developed a dynamic model for a multi-agent system comprising one leader and multiple followers, incorporating nonlinear dynamics and unknown external disturbances. The proposed controller ensures rapid finite-time convergence of tracking errors while maintaining robustness against parameter uncertainties, frictional forces, and external perturbations. The theoretical analysis, based on Lyapunov stability, rigorously proves the boundedness and convergence of all system states. Simulation results on a three-arm robotic platform validate the method’s superiority, demonstrating higher tracking accuracy, faster convergence, and stronger disturbance rejection compared with baseline controllers, including SMC, ETASMC, PID, Fixed-Time Consensus Control (FTCC), Disturbance Observer-Based Control (DOBC), and Adaptive Sliding Mode Control (ASMC). This research provides a practical and scalable solution for multi-arm coordination in unstructured environments, significantly advancing the autonomy and reliability of industrial robotic systems. Full article