Search Results (2,065)

Today, businesses are adopting digital transformation strategies to make their production processes more agile, efficient, and sustainable. At the same time, lean manufacturing principles aim to create value by reducing waste in production processes. In this context, it is important that the machine to be selected for inventory tracking can meet both the technological features suitable for digital transformation goals and the operational efficiency criteria required by lean manufacturing. In this study, multi-criteria decision-making methods were used to select the most suitable machine for inventory tracking based on digital transformation and lean manufacturing perspectives. This study applies a framework that integrates the Continuous Intuitionistic Fuzzy Analytic Hierarchy Process (CINFU AHP) and the Continuous Intuitionistic Fuzzy Combinative Distance-Based Assessment (CINFU CODAS) methods to select the most suitable machine for inventory tracking. The framework contributes to lean manufacturing by providing actionable insights and robust sensitivity analyses, ensuring decision-making reliability under fluctuating conditions. The CINFU AHP method determines the relative importance of each criterion by incorporating expert opinions. Six criteria, Speed (C1), Setup Time (C2), Ease to Operate and Move (C3), Ability to Handle Multiple Operations (C4), Maintenance and Energy Cost (C5), and Lifetime (C6), were considered in the study. The most important criteria were C1 and C4, with scores of 0.25 and 0.23, respectively. Following the criteria weighting, the CINFU CODAS method ranks the alternative machines based on their performance across the weighted criteria. Four alternative machines (High-Speed Automated Scanner (A1), Multi-Functional Robotic Arm (A2), Mobile Inventory Tracker (A3), and Cost-Efficient Fixed Inventory Counter (A4)) are evaluated based on the criteria selected. The results indicate that Alternative A1 ranked first because of its superior speed and operational efficiency, while Alternative A3 ranked last due to its high initial cost despite being cost-effective. Finally, a sensitivity analysis further examines the impact of varying criteria weights on the alternative rankings. Quantitative findings demonstrate how the applied CINFU AHP&CODAS methodology influenced the rankings of alternatives and their sensitivity to criteria weights. The results revealed that C1 and C4 were the most essential criteria, and Machine A2 outperformed others under varying weights. Sensitivity results indicate that the changes in criterion weights may affect the alternative ranking. Full article

With the escalating demand for automation in chemical laboratories, multi-robot systems are assuming an increasingly prominent role in chemical laboratories, particularly in the task of transporting reagents and experimental materials. In this paper, we propose a multi-robot path planning approach based on the combination of the A* algorithm and the dynamic window algorithm (DWA) for optimizing the efficiency of reagent transportation in chemical laboratories. In environments like chemical laboratories, dynamic obstacles (such as people and equipment) and transportation tasks that demand precise control render traditional path planning algorithms challenging. To address these issues, in this paper, we incorporate the cost information from the current point to the goal point into the evaluation function of the traditional A* algorithm to enhance the search efficiency and add the safety distance to extract the critical points of the paths, which are utilized as the temporary goal points of the DWA algorithm. In the DWA algorithm, a stop-and-wait mechanism and a replanning strategy are added, and a direction factor is included in the evaluation function to guarantee that the robots can adjust their paths promptly in the presence of dynamic obstacles or interference from other robots to evade potential conflicts or traps, thereby reaching the goal point smoothly. Additionally, regarding the multi-robot path conflict problem, this paper adopts a dynamic prioritization method, which dynamically adjusts the motion priority among robots in accordance with real-time environmental changes, reducing the occurrence of path conflicts. The experimental results highlight that this approach effectively tackles the path planning challenge in multi-robot collaborative transportation tasks within chemical laboratories, significantly enhancing transportation efficiency and ensuring the safe operation of the robots. Full article

Electrically driven legged robots have become popular in recent years. However, the development of reliable energy supply systems and effective energy management strategies for legged robots with dramatically varying power requirements still needs to be explored. This article proposes a learning-based model predictive control (MPC) energy management strategy for legged robots with battery–supercapacitor hybrid energy storage systems containing a power prediction unit and an MPC with learning-based adaptive weights. Firstly, the mathematical model of the legged robot is established, and a dual-layer long short-term memory network is constructed to predict the load power demand, providing the model and measurable disturbance for the MPC. Secondly, a multi-objective optimization objective function is established for the MPC-based energy management strategy. Three normalized terms, battery capacity loss, battery power fluctuation, and supercapacitor state-of-charge regulation, are balanced in the objective function. Finally, a deep learning algorithm is proposed to adaptively adjust the three weighting factors to meet the diverse operation conditions. Hardware-in-the-loop experimental implementations demonstrate that the proposed method can improve the kinematic performance of the legged robot by maintaining the supercapacitor state of charge at a relatively high level and reducing the battery capacity loss by 12.7% compared with the conventional MPC method. Full article

This study designs and develops a wearable exoskeleton piano assistance system for individuals recovering from neurological injuries, aiming to help users regain the ability to perform complex tasks such as playing the piano. While soft robotic exoskeletons have proven effective in rehabilitation therapy and daily activity assistance, challenges remain in performing highly dexterous tasks due to structural complexity and insufficient motion accuracy. To address these issues, we developed a modular division method based on multi-domain mapping and a top-down process model. This method integrates the functional domain, structural domain, and user needs domain, and explores the principles and methods for creating functional construction modules, overcoming the limitations of traditional top-down approaches in design flexibility. By closely combining layout constraints with the design model, this method significantly improves the accuracy and efficiency of module configuration, offering a new path for the development of piano practice assistance devices. The results demonstrate that this device innovatively combines piano practice with rehabilitation training and through the introduction of ontological modeling methods, resolves the challenges of multidimensional needs mapping. Based on five user requirements (P), we calculated the corresponding demand weight (K), making the design more aligned with user needs. The device excels in enhancing motion accuracy, interactivity, and comfort, filling the gap in traditional piano assistance devices in terms of multi-functionality and high adaptability, and offering new ideas for the design and promotion of intelligent assistive devices. Simulation analysis, combined with the motion trajectory of the finger’s proximal joint, calculates that 60° is the maximum bending angle for the aforementioned joint. Physical validation confirms the device’s superior performance in terms of reliability and high-precision motion reproduction, meeting the requirements for piano-assisted training. Through multi-domain mapping, the top-down process model, and modular design, this research effectively breaks through the design flexibility and functional adaptability bottleneck of traditional piano assistance devices while integrating neurological rehabilitation with music education, opening up a new application path for intelligent assistive devices in the fields of rehabilitation medicine and arts education, and providing a solution for cross-disciplinary technology fusion and innovative development. Full article

Magnetic hydrogel soft robots have shown great potential in various fields. However, their contact dynamic behaviors are complex, considering stick–slip motion at the contact interface, and lack accurate computational models to analyze them. This paper improves the numerical computational method for hydrogel materials with magneto-mechanical coupling effect, analyses the inchworm-like contact motion of the biomimetic bipedal magnetic hydrogel soft robot, and designs and optimizes the robot’s structure. In the constitutive model, a correction factor representing the influence of the direction of magnetic flux density on the domain density has been introduced. The magnetic part of the Helmholtz free energy has been redefined as the magnetic potential energy, which can be used to explain the phenomenon that the material will still deform when the magnetic flux density is parallel to the external magnetic field. The accuracy of the simulation is verified by comparing numerical solutions with experimental results for a magnetic hydrogel cantilever beam. Furthermore, employing the present methods, the locomotion of a magnetic hydrogel soft robot modeled after the inchworm’s gait is simulated, and the influence of the coefficient of friction on its movement is discussed. The numerical results clearly display the control effect of the external magnetic field on the robot’s motion. Full article

Adhesion-based space climbing robots, with their flexibility and multi-functional capabilities, are seen as a promising candidate for in-orbit maintenance. However, challenges such as uncertain adhesion establishment, unexpected detachment, and body motion unsteadiness in microgravity environments persist. To address these issues, this paper proposes a coordinated force–position compliance control method that integrates novel adhesion establishment and rotational detachment strategies, integrated into the gait schedule for a space climbing robot. By monitoring the foot-end reaction forces in real time, the proposed method establishes adhesion without risking damaging the spacecraft exterior, and smooth detachment is achieved by rotating the foot joint instead of direct pulling. These strategies are dedicated to reducing unnecessary control actions and, accordingly, the required adhesion forces in all feet, reducing the possibility of unexpected detachment. Climbing experiments have been conducted in a suspension-based gravity compensation system to examine the merits of the proposed method. The experimental results demonstrate that the proposed rotational detaching method decreases the required pulling force by 65.5% compared to direct pulling, thus greatly reducing the disturbance introduced to the robot body and other supporting legs. When stepping on an obstacle, the compliant control method is shown to reduce unnecessarily aggressive control actions and result in a reduction in relevant normal and shear adhesion forces in the supporting legs by 44.8% and 35.1%, respectively, compared to a PID controller. Full article

Six degrees of freedom (6-DoF) object pose estimation is essential for robotic grasping and autonomous driving. While estimating pose from a single RGB image is highly desirable for real-world applications, it presents significant challenges. Many approaches incorporate supplementary information, such as depth data, to derive valuable geometric characteristics. However, the challenge of deep neural networks inadequately extracting features from object regions in RGB images remains. To overcome these limitations, we introduce the Geometry-Focused Attention Network (GFA-Net), a novel framework designed for more comprehensive feature extraction by analyzing critical geometric and textural object characteristics. GFA-Net leverages Point-wise Feature Attention (PFA) to capture subtle pose differences, guiding the network to localize object regions and identify point-wise discrepancies as pose shifts. In addition, a Geometry Feature Aggregation Module (GFAM) integrates multi-scale geometric feature maps to distill crucial geometric features. Then, the resulting dense 2D–3D correspondences are passed to a Perspective-n-Point (PnP) module for 6-DoF pose computation. Experimental results on the LINEMOD and Occlusion LINEMOD datasets indicate that our proposed method is highly competitive with state-of-the-art approaches, achieving 96.54% and 49.35% accuracy, respectively, utilizing the ADD-S metric with a 0.10d threshold. Full article

An automated micro-tweezers system with a flexible workspace would benefit the intelligent sorting of live cells. Such micro-tweezers could employ a forced vortex strong enough to capture a single cell. Furthermore, addressable control of the position to the vortex would constitute a robotic system. In this study, a spherical micro-object composed of super paramagnetic particles tightly packed in a non-magnetic resin is rotated with a combined magnetic field of permanent magnets. The said magnetic field is articulated by an open-kinematic chain controlled with a simple adaptive PI-control scheme. A vortex is formed as the spherical particle, assumed to be submerged under the surface of fluid, and follows the position and orientation of the external magnetic field. This forced vortex induces a radial pressure gradient that captures the live cell orbiting around the spherical object combined with the inertial effects. Here, a comprehensive mathematical model is presented to reflect on the dynamics of such micro-tweezer systems. Numerical results demonstrate that it is theoretically possible to capture and tow a bacterium cell while meeting extreme tracking references for motion control. Magnetic and fluid forces on the spherical particle traverse the vortex and the bacterium cell, with orbiting and sporadic collusion of the bacterium cell around the spherical particle, and the positions of the end-effector, i.e., the magnets, are analyzed. Full article

Trajectory prediction is a critical component of autonomous driving, intelligent transportation systems, and human–robot interactions, particularly in complex environments like intersections, where diverse road constraints and multi-agent interactions significantly increase the risk of collisions. To address these challenges, a Heterogeneous Risk-Aware Graph Encoder with Continuous Parameterized Decoder for Trajectory Prediction (HRGC) is proposed. The architecture integrates a heterogeneous risk-aware local graph attention encoder, a low-rank temporal transformer, a fusion lane and global interaction encoder layer, and a continuous parameterized decoder. First, a heterogeneous risk-aware edge-enhanced local attention encoder is proposed, which enhances edge features using risk metrics, constructs graph structures through graph optimization and spectral clustering, maps these enhanced edge features to corresponding graph structure indices, and enriches node features with local agent-to-agent attention. Risk-aware edge attention is aggregated to update node features, capturing spatial and collision-aware representations, embedding crucial risk information into agents’ features. Next, the low-rank temporal transformer is employed to reduce computational complexity while preserving accuracy. By modeling agent-to-lane relationships, it captures critical map context, enhancing the understanding of agent behavior. Global interaction further refines node-to-node interactions via attention mechanisms, integrating risk and spatial information for improved trajectory encoding. Finally, a trajectory decoder utilizes the aforementioned encoder to generate control points for continuous parameterized curves. These control points are multiplied by dynamically adjusted basis functions, which are determined by an adaptive knot vector that adjusts based on velocity and curvature. This mechanism ensures precise local control and the superior handling of sharp turns and speed variations, resulting in more accurate real-time predictions in complex scenarios. The HRGC network achieves superior performance on the Argoverse 1 benchmark, outperforming state-of-the-art methods in complex urban intersections. Full article

This study investigates the integrated multi-objective scheduling problems of job shops and material handling robots (MHR) with minimising the maximum completion time (makespan), earliness or tardiness, and total energy consumption. The collaborative scheduling of MHR and machines can enhance efficiency and reduce costs. First, a mathematical model is constructed to articulate the concerned problems. Second, three meta-heuristics, i.e., genetic algorithm (GA), differential evolution, and harmony search, are employed, and their variants with seven local search operators are devised to enhance solution quality. Then, reinforcement learning algorithms, i.e., Q-learning and state–action–reward–state–action (SARSA), are utilised to select suitable local search operators during iterations. Three reward setting strategies are designed for reinforcement learning algorithms. Finally, the proposed algorithms are examined by solving 82 benchmark instances. Based on the solutions and their analysis, we conclude that the proposed GA integrating SARSA with the first reward setting strategy is the most competitive one among 27 compared algorithms. Full article

This paper proposes efficient implementations of robot audition systems, specifically focusing on deployments using HARK, an open-source software (OSS) platform designed for robot audition. Although robot audition systems are versatile and suitable for various scenarios, efficiently deploying them can be challenging due to their high computational demands and extensive processing times. For scenarios involving intensive high-dimensional data processing with large-scale microphone arrays, our generalizable GPU-based implementation significantly reduced processing time, enabling real-time Sound Source Localization (SSL) and Sound Source Separation (SSS) using a 60-channel microphone array across two distinct GPU platforms. Specifically, our implementation achieved speedups of 23.3× for SSL and 3.0× for SSS on a high-performance server equipped with an NVIDIA A100 80 GB GPU. Additionally, on the Jetson AGX Orin 32 GB, which represents embedded environments, it achieved speedups of 14.8× for SSL and 1.6× for SSS. For edge computing scenarios, we developed an adaptable FPGA-based implementation of HARK using High-Level Synthesis (HLS) on M-KUBOS, a Multi-Access Edge Computing (MEC) FPGA Multiprocessor System on a Chip (MPSoC) device. Utilizing an eight-channel microphone array, this implementation achieved a 1.2× speedup for SSL and a 1.1× speedup for SSS, along with a 1.1× improvement in overall energy efficiency. Full article

Addressing the issue of excessive manual intervention in discharging fermented grains from underground tanks in traditional brewing technology, this paper proposes an intelligent grains-out strategy based on a multi-degree-of-freedom hybrid robot. The robot’s structure and control system are introduced, along with analyses of kinematics solutions for its parallel components and end-effector speeds. According to its structural characteristics and working conditions, a visual-perception-based motion control method of discharging fermented grains is determined. The enhanced perception of underground tanks’ positions is achieved through improved Canny edge detection algorithms, and a YOLO-v7 neural network is employed to train an image segmentation model for fermented grains’ surface, integrating depth information to synthesize point clouds. We then carry out the downsampling and three-dimensional reconstruction of these point clouds, then match the underground tank model with the fermented grain surface model to replicate the tank’s interior space. Finally, a digging motion control method is proposed and experimentally validated for feasibility and operational efficiency. Full article

Surface electromyography (sEMG) signals reflect the local electrical activity of muscle fibers and the synergistic action of the overall muscle group, making them useful for gesture control of myoelectric manipulators. In recent years, deep learning methods have increasingly been applied to sEMG gesture recognition due to their powerful automatic feature extraction capabilities. sEMG signals contain rich local details and global patterns, but single-scale convolutional networks are limited in their ability to capture both comprehensively, which restricts model performance. This paper proposes a deep learning model based on multi-scale feature fusion—MS-CLSTM (MS Block-ResCBAM-Bi-LSTM). The MS Block extracts local details, global patterns, and inter-channel correlations in sEMG signals using convolutional kernels of different scales. The ResCBAM, which integrates CBAM and Simple-ResNet, enhances attention to key gesture information while alleviating overfitting issues common in small-sample datasets. Experimental results demonstrate that the MS-CLSTM model achieves recognition accuracies of 86.66% and 83.27% on the Ninapro DB2 and DB4 datasets, respectively, and the accuracy can reach 89% in real-time myoelectric manipulator gesture prediction experiments. The proposed model exhibits superior performance in sEMG gesture recognition tasks, offering an effective solution for applications in prosthetic hand control, robotic control, and other human–computer interaction fields. Full article

Developing autonomous navigation techniques for surface vehicles remains an important research area, and accurate global path planning is essential. For mobile robots—particularly for Unmanned Surface Vehicles (USVs)—a key challenge is ensuring that sharp turns and sharp breaks are avoided. Therefore, global path planning must not only calculate the shortest path but also provide smoothness. Bézier Curves are one of the main methods used for smoothing paths in the literature. Some studies have focused on turns alone; however, continuous path smoothness across the entire trajectory enhances navigational quality. Contrary to similar studies, we applied Bézier Curves whose control polygon is defined by an RRT path and thus avoided a multi-objective formulation. In the final stage of our approach, we proposed a control point reduction method in order to decrease the time complexity without affecting the feasibility of the path. Our experimental results suggest significant improvements for multiple map sizes, in terms of path smoothness. Full article

Quadruped robots, with their biomimetic structure, are capable of stable locomotion in complex terrains and are vital in rescue, exploration, and military applications. However, developing multi-modal robots that feature simple motion control while adapting to diverse amphibious environments remains a significant challenge. These robots need to excel at obstacle-crossing, waterproofing, and maintaining stability across various locomotion modes. To address these challenges, this paper introduces a novel leg–fin integrated propulsion mechanism for a bionic quadruped robot, utilizing rapidly advancing soft materials and integrated molding technologies. The robot’s motion is modeled and decomposed using an improved central pattern generator (CPG) control network. By leveraging the control characteristics of the CPG model, global control of the single-degree-of-freedom drive mechanism is achieved, allowing smooth transitions between different motion modes. The design is verified through simulations conducted in the Webots environment. Finally, a physical prototype of the quadruped compliant robot is constructed, and experiments are carried out to test its walking, turning, and obstacle-crossing abilities in various environments. The experimental results demonstrate that the robot shows a significant speed advantage in regions where land and water meet, reaching a maximum speed of 1.03 body lengths per second (bl/s). Full article