Search Results (1,795)

This study evaluates the operational potential of modernizing intraplant material flow by integrating an autonomous mobile robot (AMR) with lean logistics principles at Schneider Electric Elda SA. The baseline manual transport system was diagnosed through a quantitative red-green waste assessment, revealing capacity constraints, non-value-adding activities, and traffic congestion. To address these inefficiencies, an AMR-assisted transport architecture was developed by decoupling finished goods transport from component delivery. The proposed system was evaluated through a non-deterministic discrete-event simulation model in FlexSim, incorporating structural sensitivity analysis and stochastic Pareto-governed handling overheads. The findings suggest that a single AMR is capable of executing a simulated 24 transport operations per shift compared to the 21 pallets observed in the baseline setup while maintaining a theoretical operational reserve of 41%. However, stress-testing reveals that a 20% production surge or heavy-tailed operational disturbances compress this buffer to 26.0% and 37.5%, respectively, triggering localized average waiting times at line D13 of up to 36.0 min. As an exploratory examination of the design behavior, the limitations of a single vehicle operating without localized safety zones or ambient traffic interference under these specific structural strains are exposed. By combining Lean logistics principles with unit modeling and sensitivity analysis, the study generates scalable data and detailing completed transport and waiting times across specific scenarios, highlighting the critical limits of the simplified single-vehicle simulation. Full article

To address the urgent need for AI literacy in vocational education, we implemented a 17-week robotics-enhanced micro-major using scaffolded hardware-in-the-loop environments. A longitudinal quasi-experimental design revealed significant gains across three dimensions: architectural knowledge (+15.1%), system attitude (+7.2%), and ethical awareness (+5.8%). Behavioral telemetry confirmed a near-doubling of high-frequency AI tool adoption (34.8 to 61.1%), demonstrating sustained integration of coding assistants beyond classroom settings. These findings establish robotics-based curricula as a scalable framework for bridging the digital divide, cultivating human–AI collaboration, and preparing vocational learners for lifecycle deployment in complex cyber-physical ecosystems. Full article

Bilateral robotic rehabilitation has emerged as a technological approach for promoting coordinated upper-limb training after stroke. This state-of-the-art review critically analyzes bilateral upper-limb rehabilitation robots with emphasis on mechanical architecture, actuation and transmission, bilateral interaction modalities, control strategies, assistance modes, and validation evidence. A structured literature search covering 2010 to 8 July 2026 identified 141 records; 23 technology-related publications were retained for the state-of-the-art analysis, comprising 18 primary bilateral robotic studies and 5 supporting technical/contextual publications. The reviewed systems were organized according to a hierarchical framework distinguishing end-effector, exoskeleton, and hybrid architectures from simultaneous bilateral, master–slave/mirror-based, and cooperative bimanual interaction modalities. The evidence indicates that end-effector systems favor mechanical simplicity and adaptable workspaces, whereas exoskeletons provide more direct joint-level control at the cost of greater alignment and mechanical complexity. Control approaches increasingly incorporate impedance, admittance, assist-as-needed, and bio-signal-based strategies to improve compliant interaction and adapt assistance to user contribution. However, many advanced systems remain supported primarily by engineering validation or experiments involving healthy participants, while direct post-stroke clinical validation is comparatively limited. Future development should therefore prioritize clinically validated adaptive assistance, control strategies capable of accommodating asymmetric bilateral contribution, and safe, usable, and affordable systems suitable for clinical and home-based rehabilitation. Full article

The increasing demand for flexible, high-precision, and low-damage manufacturing is driving industrial robotic grippers toward adaptive systems with compliant interaction, force regulation, and intelligent decision-making capabilities. However, their industrial deployment remains limited by three major challenges: the trade-off between structural compliance and load-bearing capability, the insufficient coordination between sensing performance and closed-loop force control, and the limited generalization and safety validation of learning-based methods. This review presents an engineering-oriented analysis of adaptive robotic grippers based on three paradigms: structural compliance, active compliance, and learning-enabled grasping. The design principles, performance characteristics, and application limitations of compliant mechanisms, variable stiffness structures, carbon fiber composites, embedded sensing, force control, data-driven methods, reinforcement learning, and model–data fusion are discussed. A comparative framework is established according to the adaptation mechanisms, key parameters, performance boundaries, and industrial applications. The analysis shows that representative underactuated grippers typically achieve 3–19 degrees of freedom, grasping success rates of 90–98%, and load capacities of approximately 10–50 N, but remain limited in force regulation. Actively compliant grippers achieve force errors of 0.1–1 N, position errors of 0.05–0.5 mm, and control frequencies of 500 Hz–1 kHz, while learning-enabled methods require 10²–10⁴ samples for compensation and 10⁵–10⁶ interactions for reinforcement learning. The model–data fusion provides a practical balance between adaptability, interpretability, and safety. Future adaptive grippers will evolve toward integrated structure, sensing, learning, and control architectures with enhanced reliability and industrial applicability. Full article

The “Maestro Arm,” presented in this paper, is a modular wearable robotic arm with a five-fingered hand and wrist, elbow, and shoulder joints. The arm attaches to a waist belt to serve as a wearable third arm and can detach from its shoulder interface for mounting on external platforms such as a table or wheelchair. The dexterous, underactuated hand features a biomimetic joint design with 6 degrees of freedom and can output 18.4 N of grip force and 66.7 N of pulling force. A generatively designed forearm internal structure houses all necessary electronics. Cycloidal gear actuation systems control the arm’s vertical (shoulder joint) and horizontal (elbow joint) motions, providing 17 Nm and 8.5 Nm of lifting torque, respectively. The modular attachment architecture also provides a basis for future investigation of prosthetic configurations; however, this study does not cover socket design, residual-limb attachment, suspension, or clinical prosthetic use. The arm is fully controlled by an insole-based custom foot controller, called “Maestro Step.” This foot controller has two push buttons that control finger actuation and the grip pattern. The user’s ankle motion controls the shoulder, elbow, and wrist joints, with gesture recognition to switch between joints. Full article

Sequential evidence selection can reveal which parts of an existing sensor record reduce model uncertainty, while providing a computational test bed for future adaptive sensing. This work introduces the Embodied Evidence Acquisition and Reasoning Loop (EARL), a typed architecture in which five role-specialized critics score evidence requests and a deterministic safety governor retains exclusive execution authority. Observed, derived, and simulated evidence remain provenance-distinct in a replayable, hash-linked ledger. The primary experiment sequentially disclosed precomputed feature bundles from pre-recorded gait data; it did not acquire new measurements. EARL was evaluated on 64 unique subjects from the PhysioNet Gait in Neurodegenerative Disease Database using repeated subject-level cross-validation, 11 predeclared conditions, and 3520 replay-verified runs. The primary endpoint was area under cumulative posterior-entropy reduction. EARL achieved 7.689 (95% CI 7.535–7.840), exceeding fixed-order and random selection by 0.459 and 0.763, respectively; the EARL-minus-EIG difference was –0.321. EARL had descriptively higher macro accuracy (55.8% versus 49.5%) and a lower Brier score (0.781 versus 0.813) than pure expected-information-gain selection. This measures an entropy-efficiency trade-off under additional selection criteria, not universal superiority. All 10 original software safety challenges produced their expected outcomes. Separately identified post hoc analyses examine probe use, a sensitivity analysis excluding the record-quality probe, critic influence, illustrative resource costs, early stopping, and safety-constrained simulated execution. The small retrospective cohort and illustrative simulations establish software behavior, not clinical diagnostic performance, treatment benefit, physical-robot safety, or patient efficacy. Full article

Automated inspection of small metallic components is increasingly required in industrial manufacturing, particularly when dimensional conformity and geometric characteristics affect assembly quality and functional performance. This paper presents a preliminary proof-of-concept study for a collaborative SCARA-based platform intended for automated dimensional and geometric inspection of metallic plates. The study does not report a complete metrologically validated inspection cell; instead, it defines the industrial inspection problem, proposes a modular robotic architecture, and documents the preliminary implementation activities already completed. The industrial motivation is associated with metallic plates used in automotive thermal-management components, while a simplified rectangular plate is adopted for controlled development of handling, positioning, image acquisition, calibration, and initial dimensional-feature extraction. The proposed architecture separates robotic manipulation from the measurement subsystem: the SCARA robot provides repeatable handling and positioning, whereas the vision system supports preliminary calibrated in-plane measurement. The robotic platform is based on the PSR-20 collaborative SCARA robot (SmileTech, Portugal), selected due to its compact footprint, repeatable planar motion, affordable cost and suitability for automated pick-and-place inspection tasks. The implemented activities include SCARA workspace simulation, end-effector design, camera integration, intrinsic camera calibration, measurement-plane calibration, and preliminary calibrated 2D dimensional measurements. The experimental validation reported in this study is currently limited to in-plane measurements of length and width. Height, thickness, flatness, and surface-form inspection are identified as future extensions and have not yet been experimentally validated. The results show repeatable measurements under the tested conditions for a high-contrast reference part, while the representative metallic part remains limited by segmentation robustness and contour-definition uncertainty. Remaining work includes a formal uncertainty analysis, broader validation with calibrated reference artefacts, robust segmentation, and out-of-plane sensing. Full article

With the rapid expansion of modern facility agriculture, harvesting robots for tomato (Solanum lycopersicum L.) and other solanaceous fruits have become key equipment for alleviating labor shortages. However, in unstructured greenhouse and open-field scenarios, branch and leaf occlusion, overlapping fruit clusters, variable illumination, and fragile fruit tissues constrain perception reliability and mechanical contact safety. Embodied intelligence, a closed harvesting loop integrating perception, spatial reasoning, motion control, and physical-contact feedback, offers a promising paradigm to address these challenges. Nevertheless, the transition from prototypes to reliable commercial deployment remains constrained by environmental variability, biological heterogeneity, and system-level integration. This review systematically examines the mechanisms and process architectures for converting multimodal perception into low-damage harvesting actions of solanaceous fruit-picking robots. First, the review analyzes deep-learning-based real-time recognition methods, covering target detection, instance segmentation, and occlusion-adaptive strategies. Second, attention turns to spatial 3D localization and pedicel feature acquisition, including depth sensing and high-precision hand–eye calibration. Furthermore, operation patterns and flexible low-damage end-effectors are examined, clarifying fruit drop collision damage and physical contact models of suction and shearing devices. Finally, technical bottlenecks and future directions are discussed, encompassing multi-modal perception–action coupling, agricultural foundation models, end-to-end closed-loop control, and commercialization requirements. Overall, it links algorithmic perception accuracy with system-level harvesting reliability, proposes a crop-specific, damage-aware evaluation framework, and provides a roadmap for robust, low-damage commercial deployment. Full article

Automated bidirectional charging of electric vehicle fleets offers massive energy system benefits that have barely been leveraged so far. Inductive charging, due to its contactless power transfer, represents a particularly robust solution for automation and avoids the mechanical wear and robotic-handling requirements inherent to conductive systems with high plug-in cycles. This article investigates scalable topologies for inductive charging infrastructure with per-point power levels up to 22 kW. For this purpose, an N-box design architecture is introduced to systematically map power electronics sub-components into functional boxes between the grid interface and charging pads. The proposed framework thus enables a comparative cost assessment of supply schemes, i.e., DC link, 50 Hz AC, and 85 kHz high-frequency power distribution. The results show that using an optimized N-box architecture with grouping of four to seven charging points reduces the total CAPEX costs of an infrastructure from two to 50 parking lots by up to 32% on average compared to scaling state-of-the-art designs from private inductive home charging. Architectural grouping is therefore identified to be more important than the choice of power electronic topology. Further conclusions are listed at the end of the article. Full article

Series Elastic Actuators (SEAs) have been widely adopted in collaborative robots, rehabilitation robots, and other compliant robotic systems owing to their excellent compliance and force-control performance. However, the introduction of elastic elements also increases dynamic complexity, giving rise to nonlinearities, parameter uncertainties, and oscillations. To address these issues, this paper proposes a Transformer-based temporal reinforcement learning control method for SEAs within the Proximal Policy Optimization (PPO) framework. First, a Transformer replaces the conventional Multi-Layer Perceptron (MLP) policy network to extract temporal dependency features from observation sequences via the self-attention mechanism. Second, a fixed-length historical state window is incorporated into the policy input to mitigate the performance degradation caused by partial observability (POMDP). Both simulation and hardware experiments validate the proposed method. In simulation, it achieves superior transient performance (a 10–90% rise time of 0.111 s and an overshoot of 3.68%) together with stable sinusoidal tracking. Real-world tests on a physical SEA platform further confirm its practical feasibility: multi-target step tracking attains a 10–90% rise time of approximately 0.15 s with overshoot below 2.3%, whereas long-duration sinusoidal tracking (60° amplitude, 0.1 Hz) maintains an RMS error of approximately 2.3° and smooth, chatter-free control actions. Comparative studies against MLP, LSTM, and CNN architectures reveal that the Transformer policy offers significant advantages in suppressing elastic oscillations and generating smooth control commands, confirming the efficacy of temporal modeling for the complex dynamics of SEA systems. An ablation study over the historical window length (L = 1–8) shows that at least four history steps are required to suppress elastic oscillations under fast target switching, while the mean inference time remains below 0.81 ms for L ≤ 8. In hardware payload experiments (0–1200 g), the tracking RMSE increases monotonically from 7.70° to 8.55° and the peak overshoot from 2.50% to 8.53%, while all runs remain stable without controller fault or divergence; the complete control task, including Transformer inference, executes within 0.61 ms on the real-time controller. Full article

The adoption of robotics in construction has progressed more slowly than in many other sectors. Building information models (BIMs) contain information that can support construction robotics, while robots require task-specific project data, such as geometry, location, material, sequence, and operating constraints, that may not be readily available in a directly usable form. This study proposes a conceptually integrated system architecture for BIM-to-robot information exchange comprising Task Planning, Task Decomposition, and anticipated Robot Task Execution linked by two information exchanges. A 20-concrete-masonry-unit (CMU) wall case study demonstrates selected information-preparation and documentation portions of the architecture. A low-LOD Revit wall was decomposed into individual CMUs using Dynamo, and component location (X, Y, Z, and orientation), material type, and identification (I.D.) information were extracted and formatted as robot-oriented task information. Because the available robotic platform lacked manipulation capability, a human worker interpreted the exported task information and constructed the wall, while a Husky A200 robot collected site images for dense point-cloud reconstruction. The reconstruction was superimposed on the source Revit model to qualitatively assess consistency between the constructed wall and the intended BIM-derived layout. The case study therefore demonstrates BIM-derived information generation and extraction, worker interpretation and use of the task information, and robot-assisted documentation, but it does not verify autonomous robotic construction. The primary contribution is the architectural integration of prior information-exchange and parametric-modeling methods across the end-to-end BIM-to-robot workflow, including explicit information requirements and exchange points; the term end-to-end refers to architectural scope rather than end-to-end experimental validation. Full article

Over the last few years, cyber-physical systems (CPSs) have come to play a central role in critical infrastructures, manufacturing, transport, and robotics. As a consequence, their lack of security increasingly affects the physical world, possibly causing material damage, environmental harm, and even loss of life. This paper reviews the evolution of CPSs over the last decade and highlights their main security issues and remedies. Some particularly relevant software infrastructures and communication protocols are analyzed in detail, such as the Robot Operating System (ROS), Supervisory Control and Data Acquisition (SCADA), and OPC Unified Architecture (OPC UA). The most important vulnerabilities are described, for instance, the ones affecting the Data Distribution Service (DDS) of ROS version 2, as well as the extent of insecure ROS and OPC UA deployment on the Internet. Moreover, the role and impact of Artificial Intelligence (AI) as an offensive and defensive tool is also discussed. Finally, we argue that the transition towards memory-safe and verifiable programming languages, such as Rust, and the use of model-based design (MBD) methods and tools might help prevent entire classes of attacks in the future. Full article

Human–Object Interaction (HOI) detection seeks to identify the relationships between humans and objects in images that play a pivotal role in high-level vision tasks and biomimetic systems, such as biomimetic robotics, intelligent prosthetics, and embodied AI for intent understanding. However, existing approaches that rely solely on visual appearance features are susceptible to background interference, which adversely affects detection accuracy. Inspired by the biomimetic dual-stream mechanism of biological visual perception, we propose a Transformer-based HOI detection model with a dual-branch parallel fusion architecture, incorporating a skeleton topology branch alongside the standard image branch. The skeleton branch leverages a Graph Convolutional Network (GCN) to explicitly model spatial–kinematic relationships between human keypoints and objects, providing fine-grained topological priors to complement visual appearance features before joint decoding. Our approach achieves 51.6% Mean Average Precision (mAP) on the Verbs in Common Objects in Context (V-COCO) dataset, outperforming the Transformer-based HOI baseline by 2.7 mAP points, highlighting its effectiveness in enhancing perceptual robustness for biomimetic interactive applications. Full article

Thermal comfort is a key determinant of human health and requires adaptive responses to dynamic environments. Here, we report a temperature-adaptive textile enabled by a tensile stress mismatch-driven poly(N-isopropylacrylamide) (PNIPAM) actuator operating within a human-friendly temperature range of 18–38 °C. A pre-stretched polyurethane core fiber integrated within a PNIPAM sheath in a noncoaxial configuration induces programmable bending through tensile-stress mismatch between elastic recovery and hydrogel swelling. Unlike conventional bilayer hydrogel actuators based on differential swelling between laminated layers, this pre-stretching strategy amplifies structural deformation through elastic restoring stress. When extended to a two-dimensional textile architecture, this strategy enables reversible, dynamic pore modulation with an approximately 400% increase in pore area. This study provides a promising platform for smart adaptive textiles, wearable healthcare, and soft robotics. Full article

During continuous operation on the human back, the actual contact force exerted by a massage robotic arm may deviate from the desired value because of soft-tissue viscoelasticity, body-surface curvature changes, respiratory motion, and random disturbances. To achieve stable constant-force tracking, we propose a coordinated method combining an Extended State Observer (ESO)-enhanced proportional–integral–derivative (PID) controller with a temporally enhanced Soft Actor–Critic (SAC) algorithm to address response lag and high-frequency oscillations under complex noise. The two-layer architecture integrates fast compensation and policy optimization. In the PID-based layer, the ESO estimates the contact-force error, its first derivative, and the total disturbance; these estimates are used to schedule the PID gains and shape the controller output, improving contact establishment and continuous tracking. In the optimization layer, an improved SAC network adds Q-value-guided attention and frequency-gating constraints to long short-term memory (LSTM)-based sequence encoding, improving the utilization of historical states and suppressing high-frequency oscillations. Validation is conducted through PyBullet simulations of dynamic massage environments and experiments across stiffness levels of 1000 N/m, 2000 N/m, and 3000 N/m and target forces of 5 N, 8 N, and 10 N, demonstrating a certain degree of robustness to parameter variations. Under all conditions, the force error remains within ±0.3 N during stable tracking. Full article