Search Results (2,163)

Modern fulfillment centers share floor space with human workers, making warehouse multi-robot task allocation a safety-critical problem. We propose SHARP (Safe Heterogeneous Allocation with Risk Prediction), a Transformer-based constrained reinforcement-learning framework with a closed-form deployment-time safety mask. Under a Gaussian pedestrian belief and fixed closest-approach directions, the mask uses Bonferroni-allocated per-pair CVaR scores; a nonnegative mask score implies a conservative trajectory-level chance constraint under the stated assumptions. We also present an idealized primal–dual surrogate analysis, without claiming global convergence for the nonconvex Transformer/PPO implementation. Expanded experiments use ten training seeds per learned method and deterministic final-checkpoint evaluation on twenty independently generated held-out instances. No statistically significant difference between SHARP and Lagrangian-PPO was detected in any of the four scenarios. The held-out analysis further reveals late-training instability and severe over-conservatism in the dense S40_high scenario. These findings position SHARP as an auditable geometric filtering mechanism, while identifying conservatism and training stability as important limitations for deployment. Full article

Background: Container terminals are crucial nodes in global supply chains, but they also contribute significantly to environmental pollution. The analysis of sustainability in port logistics through carbon footprint offers crucial knowledge on how to reduce environmental impact in logistics. Methods: This systematic review uses a PRISMA-based research flow to extract key facts about energy consumption and greenhouse gas emissions, particularly CO₂, which are still prevalent in terminal operations and logistics. Results: The paper analyses strategies and technologies adopted to reduce the carbon footprint, such as efficient infrastructure, electrification, automation, digitalisation, and AI-powered port logistics. It highlights the potential of sustainable logistics solutions, such as real-time cargo tracking, intelligent robotics and data analytics, to make container terminals more eco-friendly. Conclusions: Beyond analysing sustainability assessment models for the ecological efficiency and operational performance of container terminals, this paper highlights the need for future applied research into how investments in sustainable practices, as demonstrated by the most successful Asian port examples, can further reduce container terminal environmental footprint. Full article

Industrial robots are an important strategic resource for manufacturing firms to achieve automation and intelligent development, and their role in corporate risk management has become increasingly prominent. Using data on Chinese A-share-listed manufacturing firms from 2012 to 2023, this paper examines the impact of industrial robot adoption on firms’ risk-taking levels. The results show that for every one-unit increase in industrial robot application, the firm’s risk-taking level increases by 0.206 and 0.384 units, respectively. Mechanism analyses indicate that the use of industrial robots can reduce agency costs and enhance innovation capability, thereby promoting higher levels of corporate risk-taking. Further analysis reveals that the positive effect of industrial robot adoption on firms’ risk-taking is significant only for privately owned firms, firms facing high financing constraints, firms with a higher proportion of technical employees, and firms located in regions with high innovation network density. Meanwhile, the relationship between corporate risk-taking and firm value exhibits an inverted U-shaped pattern, indicating that firms should adhere to the principle of moderation when introducing industrial robots, so as to avoid potential damage to firm value caused by excessive or blind investment. This study extends the literature on industrial robots and corporate risk-taking and provides important implications for Chinese manufacturing firms seeking to enhance their risk-taking capacity through the adoption of intelligent technologies. Full article

At present, although there are many SCARA manipulator solutions with vertical lifting functionality, they generally suffer from high maintenance costs and complex structures. Moreover, systematic performance evaluations based on international standards are lacking, leading to unclear critical performance boundaries such as accuracy and payload in practical applications. To address these issues, this paper designs and manufactures a low-cost SCARA manipulator for educational and research demonstrations as well as light-duty electronic parts assembly scenarios. A “leadscrew + stepper motor” scheme is adopted for vertical lifting, and an Arduino Mega 2560 development board serves as the core controller, significantly reducing system cost. A three-dimensional model is established using SolidWorks 2022, and kinematic simulations are carried out with MATLAB 2024a to preliminarily verify the feasibility of the mechanism. Subsequently, a physical prototype is built and experimental tests are conducted in accordance with the ISO 9283 standard. The experimental results show that the repeatability of the manipulator is controlled within the range of 0.05–0.3 mm, the path deviation caused by vibration lies between −0.52 mm and 0.3 mm, and the maximum payload capacity is 3.91 N. These experimental data can serve as a benchmark for the design and performance comparison of similar low-cost manipulators. Full article

Accurate positioning is essential for inspection robots in caged chicken houses, where long straight corridors, sparse textures, and repetitive structures challenge conventional methods. This paper proposes CVIWM (Coupled Visual-Inertial-Wheel Odometry with Markers), a tightly coupled state estimation method that fuses visual, inertial measurement unit (IMU), wheel odometry (WO), and fiducial marker observations within a factor graph optimization framework. Wheel odometry preintegration suppresses IMU horizontal drift and provides absolute scale, while sparse AprilTag markers (10 m spacing) periodically reset accumulated errors. Experiments in an 80 m corridor of a commercial caged chicken house at 0.116 m/s and 0.232 m/s showed that CVIWM achieves average positioning errors of 2.402 cm and 3.253 cm. This high precision ensured reliable image acquisition (image shift $<83$ pixels), enabling 95.7% dead hen detection and 98.9% egg detection accuracy. CVIWM offers a low-cost, easy-to-deploy, high-accuracy solution for automated poultry house inspection, supporting smart livestock farming. Full article

Robotic assistive devices, such as exoskeletons, are increasingly employed in walking rehabilitation. Therefore, the measurement of both movement kinematics and cognitive workload is important to understand this human–robot interaction in real-world contexts. To address this need this study presents the validation of a framework integrating inertial motion capture (Xsens) and eye-tracking sensor (Pupil Neon) within a Mixed Reality (Meta Quest 3) architecture. We developed an overground dual-task paradigm in which holographic numbers appear in the user’s peripheral vision. This setup actively stimulates visuospatial attention while quantifying kinematic and cognitive output. To validate the framework, the protocol has been tested on 30 healthy subjects across repeated exoskeleton training sessions. Statistical analyses revealed that the Coefficient of Multiple Correlation (CMC) and Spectral Arc Length (SPARC), calculated on the shank angular velocity, together with the Step Length Variability, exhibited significant time effects (p < 0.01), mapping the transition toward automated gait. Concurrently, pupillometric data demonstrated a measurable reduction in neurocognitive demand; specifically, the Task-Evoked Pupillary Response (TEPR) decreased significantly across progressive training sessions (p < 0.05). With this work, we validated a measurement protocol that aims to provide a novel methodology for objectively evaluating motor and cognitive adaptation in wearable assistive devices. Full article

This paper presents a battery cell joining solution leveraging adhesively bonded lithium-ion cells as a foundation for scalable, serviceable, and recyclable energy storage platforms. The proposed design methodology enables mechanically and electrically functional connections and supports a design concept intended for compatibility with automated manufacturing and future robotic disassembly. A123 26650-format cells were tested using Epo-Tek 430 conductive adhesive, with performance evaluated through ESR and G-force measurement experiments. The results indicate that no measurable change in electrical performance was observed within the resolution of the measurement system, while supporting a design concept intended to improve modularity and serviceability. The proposed system shows potential for further investigation in electric vehicle and industrial energy system applications, although further validation under realistic operating conditions is required. Full article

Autonomous navigation is a key requirement for underground mine automation, where the choice of a suitable global path planner plays a significant role. In this study, four representative planning approaches—Dijkstra’s algorithm, A*, Rapidly exploring Random Tree (RRT*), and Particle Swarm Optimization (PSO)—were evaluated on a differential-drive mobile robot within the ROS navigation framework. The algorithms were tested in two simulated underground environments: a room-and-pillar layout with relatively open space and multiple path alternatives and a narrow tunnel scenario designed to reflect more constrained mining conditions. The results indicate that Dijkstra’s algorithm consistently produced the shortest paths with the lowest computation times, while A* showed comparable performance with slightly higher computational effort. RRT* required modifications to operate effectively in narrow tunnels and exhibited significantly longer planning times. PSO, although capable of generating near-optimal solutions in open spaces, showed limitations in constrained environments due to collision handling and path feasibility issues. Differences in replanning behavior were observed when unknown obstacles were introduced. Overall, graph-based planners such as A* and Dijkstra’s algorithm demonstrated more stable and predictable performance. Future work will focus on validating these findings in real mining environments, particularly considering wheel slippage, sensor noise, and path generation challenges in narrow tunnel conditions. Full article

Berry thinning is a fundamental operation in modern vineyard management, and future robotic thinning systems have the potential to reduce labor intensity and improve operational consistency. However, automated berry thinning under field conditions is still constrained by insufficient berry-level segmentation accuracy, difficulty in recognizing occluded berries, and high missed-detection rates for small berries. These limitations mainly arise from dense berry arrangements, severe mutual occlusion, and the subtle visual features of small targets. To address these challenges, this study developed a lightweight grape berry instance segmentation and thinning decision-support method based on YOLOv8n-seg. A two-stage knowledge distillation strategy, using Mask R-CNN and YOLOv8l-seg as teacher models, was combined with 30% backbone pruning to improve the recognition of occluded and small berries while maintaining model efficiency. Subsequently, the DBSCAN clustering algorithm was used to analyze berry centroid coordinates and equivalent diameters extracted from instance segmentation masks, thereby generating preliminary thinning-target recommendations based on local berry density and berry size. The model was trained and evaluated on a self-constructed dataset containing 330 valid grape bunch images collected in 2025 from Yongming Vineyard, Lin’an District, Hangzhou, Zhejiang Province, China. The results showed that the optimized YOLOv8n-seg model achieved a box $mAP50\text{-}95$ of 0.8945 and a mask $mAP50\text{-}95$ of 0.7910, with an inference speed of 119.19 $FPS$ and 3.26 M parameters on an NVIDIA RTX 3060 Laptop GPU. Compared with the original YOLOv8n-seg model, the optimized model improved mask $mAP50\text{-}95$ by 1.20 percentage points, increased inference speed by 71.79 $FPS$, and reduced the number of parameters by 2.38 M. These results indicate that the proposed method improves grape berry instance segmentation performance while achieving a favorable balance among segmentation accuracy, lightweight characteristics, and inference efficiency. The proposed framework provides an offline RGB-based visual perception and preliminary thinning decision-support method for future grape berry thinning robots. However, because the current dataset was collected from Shine Muscat grape bunches at the berry enlargement stage in a single vineyard using the same imaging setup, the results should be interpreted as preliminary evidence under the specific cultivar, growth stage, vineyard, and imaging conditions of this study. Further validation across different grape cultivars, growth stages, vineyards, production seasons, camera systems, embedded platforms, and real robotic thinning operations is still required. 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

The transition toward smart grids and Industry 4.0 demands a fundamental shift in maintenance strategies, as manual inspection methods are increasingly being supplanted by automated monitoring systems. Among the advanced technologies for smart inspection, infrared imaging has advantages including non-contact operation, intuitive visualization, and predictive capabilities, which has become a cornerstone for autonomous inspection of critical power infrastructure. This review provides recent advancements in infrared imaging, with a specific focus on automated power system inspection. The discussion starts with an overview of the fundamental principles and system architectures, emphasizing the pivotal role of infrared detectors. A detailed analysis traces the technological evolution from traditional photon detectors to current uncooled microbolometers, and critically assesses emerging low-dimensional materials. The analysis highlights inherent performance trade-offs among sensitivity, operating temperature, and fabrication cost. Subsequently, the review explores advanced signal processing algorithms, such as real-time non-uniformity correction and adaptive noise suppression, which are typically implemented on FPGA platforms. Advanced optical configurations—encompassing computational imaging, lensless designs, and scattering suppression methods—are also discussed, demonstrating how their convergence enhances image fidelity and operational reliability in complex field environments. Representative application paradigms are surveyed, including drone-based transmission line inspections, patrol robots in substations, and fault diagnosis in photovoltaic plants; for each, operational efficacy and economic benefits are assessed. Despite considerable progress, several challenges persist, notably the performance–stability–cost trilemma in novel detector development, the substantial computational demands of end-to-end optimized systems, and a lack of standardization. Finally, the review outlines future research directions, such as high-performance uncooled arrays, AI-driven co-design of optics and algorithms, and the development of standardized, low-cost, intelligent inspection platforms. Full article

To address the rigid temporal constraints and high-precision trajectory tracking requirements in modern industrial automation (e.g., high-speed pick-and-place or collaborative assembly), this paper proposes a novel composite control strategy for robotic manipulators that integrates Actor–Critic reinforcement learning with predefined-time sliding mode control (PTC-RLC). Existing predefined-time control (PTC) schemes usually rely on excessively large switching gains when dealing with strong disturbances, which easily triggers severe chattering in the system’s actuators and degrades dynamic performance. To this end, a novel predefined-time sliding surface based on artificial delay feedback is designed, ensuring that the position tracking error can strictly converge within a user-explicitly set time $T_c$ regardless of the system’s initial states, thereby significantly enhancing temporal determinism. Meanwhile, a reinforcement learning agent based on the Actor–Critic architecture is constructed to approximate and dynamically compensate for the system’s lumped unknown dynamics and external disturbances online, minimizing the control law’s reliance on large robust gains. Based on Lyapunov stability theory, the semi-global uniform ultimate boundedness of the closed-loop system is strictly proved. Numerical simulation results demonstrate that under severe operating conditions with parameter mismatches and time-varying disturbances, the proposed control strategy not only achieves high-precision and singularity-free trajectory tracking within the predefined time, but also effectively suppresses high-frequency chattering phenomena compared to the traditional non-singular terminal sliding mode control (NTSMC), outputting a smoother control torque and demonstrating strong potential for practical engineering implementations. Full article

The increasing complexity and distributed nature of Robot Operating System (ROS)-based robotic systems require advanced Fault Detection and Diagnosis (FDD) approaches that operate autonomously with minimal human intervention. The goal of this systematic literature review is to investigate how observability-driven FDD can be automated in ROS-based robotic systems to minimise human effort. Through this lens, the review surfaces four recurring gaps that collectively limit observability-driven automation: rich telemetry sources—logs, traces, and metrics—exist in isolation and are rarely integrated into real-time detection pipelines or leveraged collectively to improve failure diagnostics; online monitoring enables automatic fault detection but depends heavily on predefined rules and expert configuration and interpretation; failure explanations are generated post hoc and rely heavily on logs; and systems remain largely reactive, lacking the continuous monitoring infrastructure needed to anticipate faults before they propagate. Although Large Language Models (LLMs) show considerable promise for automated fault explanation and natural language interaction with robotic systems, current implementations fall short of comprehensive, real-time monitoring that unifies logs, traces, metrics, and sensor streams with Artificial Intelligence (AI) reasoning. To address these gaps, this paper motivates hybrid architectures that combine observability-first design, runtime monitoring, static analysis, and agentic LLM-based reasoning, laying the groundwork for more proactive and autonomous fault management in ROS-based systems. Full article

The objectives of this study were: (1) to identify factors influencing the performance of dairy cows in an automated milking system (AMS); (2) to construct a synthetic robotic adaptability index (RAI) of cows’ adaptation to the AMS; (3) to evaluate the predictive capabilities of traits describing the milking process and RAI; and (4) to compare the predictive power of different modeling approaches. The data on 796 primiparous Polish Holstein–Friesian cows (40,233 milkings) were obtained from the milking robot management system. Milking efficiency (ME), and the average number (AA) and time (AT) of the teat cup attachments and RAI served as predicted variables. Days in milk, and four AMS milking-related and 18 linear conformation traits were used as predictors. The highest predictive ability for ME was achieved with multilayer perceptron (R² = 0.895), followed by linear regression. For AA, AT, and RAI, the highest R² values were obtained for LASSO regression (0.663, 0.642 and 0.670, respectively). The key factors determining milking performance were functional variables, particularly milk flow rate (MilkFlow) and the number of failed milking attempts (Failure), while conformation traits had limited significance. More complex machine learning models do not always lead to improved prediction quality compared to statistical methods, which emphasizes the need for a critical approach to their application in the analysis of production data. 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