Search Results (3,290)

Digital-twin-enabled human–machine collaboration (HMC) has increasingly been proposed as a system-level approach for connecting human operators, robots, sensors, artificial intelligence modules, and manufacturing resources. However, the literature varies substantially in what is called a digital twin, how physical and virtual models are coupled, whether models are updated from physical data, and how far systems have progressed beyond simulation or controlled laboratory demonstrations. This structured integrative review examines the conditions under which a digital twin can function as an integration layer for HMC in sustainable smart manufacturing, rather than assuming that such integration is already established industrial practice. The literature corpus was assembled through searches of the Web of Science Core Collection, Scopus, and IEEE Xplore, complemented by Google Scholar-based citation tracking and backward and forward citation tracing. The core search focused on studies published from 1 January 2020 to 5 August 2026, while earlier seminal studies were retained to support definitions and historical context. Studies were screened using explicit criteria for manufacturing relevance, physical–virtual coupling, state synchronization or model updating, feedback capability, and validation setting, and were critically coded by model type, integration mechanism, deployment maturity, and sustainability evidence. The review compares multimodal perception and human-state modeling, intention understanding and augmented interaction, task allocation and shared planning, digital-twin architectures, adaptive control and safety verification, and human–AI decision-making. The evidence indicates that digital twins are promising as coordination and verification layers, but many reported systems remain conceptual, simulation-based, or limited to controlled physical prototypes. Key barriers include model fidelity, online model updating, real-time synchronization, cross-platform interoperability, safety assurance, human-data governance, and the limited availability of directly measured sustainability outcomes. Future work should prioritize validated hybrid models, traceable model-update mechanisms, staged virtual-to-physical deployment, interoperable data contracts, and longitudinal evaluation of technical, human, economic, and environmental performance. Full article

Flexible pressure sensors serve as core sensing components for wearable health monitoring systems, electronic skins for soft robots, and flexible human–machine interaction devices. Benefiting from the interfacial electric double-layer polarization effect, iontronic sensing delivers far higher pressure response sensitivity than conventional parallel-plate capacitive sensors, endowing it with distinctive advantages in the detection of weak physiological signals. Nevertheless, current dense ionic thin-film dielectric layers suffer from limited deformation space under compression and poor low-pressure sensing capability. Mainstream high-precision micropillar arrays are fabricated via photolithography, 3D printing, and metal etching molds, which require costly equipment and complicated fabrication procedures, making large-area mass production unfeasible. Random frosted concave-convex microstructures feature disordered dimensions, leading to severe device hysteresis and narrow linear ranges, which fail to achieve ultrahigh sensitivity alongside a wide pressure detection range simultaneously. To address the aforementioned multiple bottlenecks, this paper proposes a low-cost resin template replication process to fabricate TPU-based ionic thin-film dielectric layers with ordered micropillar array microstructures. Combined with inkjet-printed silver conductive PI flexible electrodes, an iontronic flexible pressure sensor with a sandwich layered structure is constructed. Multi-dimensional investigations including microscopic morphology characterization, electromechanical sensing performance calibration, and human wearable application tests are systematically implemented to thoroughly elucidate the synergistic enhancement mechanism of the arrayed micropillars. Test results demonstrate that the effective pressure detection range of the sensor spans 0–1038 kPa, accommodating ultra-low pressures such as pulse signals as well as medium-to-high-pressure loads including joint bending. The sensitivity reaches 23.27 kPa⁻¹ within the low-pressure range of 0–200 kPa and remains stable at 3.52 kPa⁻¹ in the high-pressure range of 200–1038 kPa, with piecewise linear fitting correlation coefficients of 0.93 and 0.96 respectively. Both the response time and recovery time of the device are 40 ms, and the hysteresis error throughout the loading-unloading cycle is merely 2.62%. After 20,000 consecutive cyclic loading-unloading tests, the peak capacitance output only decays by 5.1%, verifying outstanding mechanical fatigue resistance and electrical stability. Validations in multi-scenario applications prove that the sensor can accurately capture human physiological and motion signals including radial artery pulses, laryngeal deformation induced by multi-syllable vocalization, and multi-angle bending of fingers and elbow joints, suitable for home-based health monitoring, quantitative rehabilitation training, flexible tactile interaction and other scenarios. The entire fabrication process eliminates high-precision micro-nano processing equipment such as photolithography systems, plasma etchers and 3D printers; only general chemical raw materials and conventional laboratory instruments are adopted. The reusable templates enable low manufacturing costs and large-area coating forming, offering a novel low-cost technical solution for the engineering implementation and industrialization of high-performance iontronic flexible pressure sensors. Full article

In industrial robot trajectory planning, trajectory segmentation has crucial importance in distinguishing between different geometric primitives, such as straight lines and arcs. Separating these elements facilitates allocating optimized motion instructions, customized to each segment category. This distinction ensures both improved execution smoothness and better operational performance. For this purpose, the Bidirectional Long Short-Term Memory (Bi-LSTM) machine learning algorithm has been implemented to segment trajectories into linear and arc-shaped parts, for which dedicated robotic commands can be used. First, several Bi-LSTM models with different architectures were trained using a synthetic dataset containing different shapes with labelled segments. Then, a theoretical study was performed to evaluate the accuracy of recognizing different shape segments using a test dataset. Finally, the generated trajectories, which implemented the best machine learning model, were transferred into the RoboDK software to launch the robot. Two different methods were used to generate trajectories for the UR3 industrial robot. The original trajectory was generated using linear interpolation only, while the second was generated using the machine learning algorithm. The experimental results show significant differences in terms of the smoothness and velocity profiles between these two trajectory generation methods. By enabling automatic classification of trajectory segments into line and arc primitives using the Bi-LSTM-based approach, the execution time is reduced by up to 43.5% and the vibration amplitude by up to 27.4% at higher speeds around 250 mm/s. However, this came at the cost of reduced accuracy at high speed, with reproduction error reaching 1.4–1.9 mm versus 0.46–0.7 mm for linear interpolation. Full article

In the domain of rotating machinery fault diagnosis, challenges such as multi-operating condition distribution heterogeneity and the difficulty of distinguishing fault features within multi-scale temporal signals persist. To address these issues, this paper introduces the Time-Gated Multi-Expert Generative Adversarial Network (TGME-GAN), a fault diagnosis approach that integrates a multi-expert gated conditional generative adversarial network with a clustering structure-aware feature enhancement. This method combines unsupervised K-means clustering with supervised discriminative learning. The optimal number of clusters is selected adaptively using the silhouette coefficient, and the distance vector from each sample to the cluster centers serves as a topological prior feature. A spatial–temporal joint representation matrix is then formed by concatenating PCA principal components, differential features, cumulative statistical features, and standardized change rates, which together capture both abrupt mutations and progressive degradation in fault signals. In the model, the discriminator incorporates a multi-expert gated network. Each expert learns a feature subspace corresponding to a distinct operating condition, and the gated network dynamically assigns fusion weights, allowing the discriminator to capture heterogeneous distributions across industrial conditions. The generator extracts multi-scale local patterns with a three-layer one-dimensional convolutional network and models sequential dependencies with a two-layer LSTM, producing high-quality fault samples that preserve intrinsic consistency. At the engineering level, TGME-GAN is deployed for gearbox fault diagnosis in uneven, small-sample industrial settings. In two gearbox fault experiments, this method substantially outperforms current mainstream models. Full article

This study investigated the application of Covariant Hamiltonian Optimization for Motion Planning (CHOMP) in the MATLAB programming environment to an industrially relevant Universal Robots UR5e six-DOF manipulator. The parameters were set to be equal to those of the standard MoveIt2 CHOMP plugin, and the obstacle cost was computed directly in MATLAB using the Robotics System Toolbox’s forward kinematics function to obtain the end-effector position at each trajectory waypoint, which was then evaluated against a piecewise potential field defined over three spherical obstacles in the workspace. We executed five distinct picking task examples and one task over thirty trials, together with a sensitivity analysis over the weight parameter defining the optimization smoothness (i.e., weight/gamma). The mixed empirical results exposed major drawbacks of vanilla CHOMP under our parameter configuration. We achieved a collision-free result for only two of the five tasks, T-03 and T-05, with T-03 converging quickly in five iterations (0.16 s) and T-05 requiring 156 iterations and hitting the planning timeout limit of 10 s. Three tasks did not yield any collision-free result under the 10 s time limit. One of those three tasks, T-01, when running 30 random trial simulations after adding a tiny amount of noise to the start/end poses, yielded 0%, so all trials timed out on its planning 200-iteration limit with an invalid collision result. We analyzed the movement profile (position, velocity, and acceleration over time) of the trajectories generated during the experiments. Several examples exceed the UR5e velocity limit (180 deg/s) and the UR5e acceleration limit (400 deg/s²) by an order of magnitude, and peak values on T-02 reached up to 4731.92 deg/s². With these chosen parameters, basic CHOMP is not industrially suitable for the UR5e robot or for the implementation of the empirical evaluation of CHOMP discussed in this paper. We also identified the modes of failure of basic CHOMP under these parameters and discuss relevant changes. Full article

Human–robot collaborative assembly line balancing and scheduling constitutes an NP-hard combinatorial optimization problem involving the simultaneous optimization of task assignment, resource allocation, processing mode selection, station-level scheduling, and ergonomic constraints. This study proposes a Q-learning-based hyper-heuristic genetic algorithm (QLHH-GA) to solve the cost-oriented ergonomic mixed-model human–robot collaborative assembly line balancing and scheduling problem. The proposed approach integrates bio-inspired evolutionary mechanisms of population variation and selection with adaptive, Q-learning-guided low-level heuristic selection. The Q-learning layer uses performance feedback to adapt the search strategy to different solution states while maintaining solution feasibility. A mixed-integer linear programming (MILP) model is also developed to minimize the total operating cost, including station opening, labor, robot operation, and energy consumption costs, while enforcing station-level energy expenditure (EE) limits. Computational experiments conducted using benchmark instances of varying sizes and a literature-based industrial case study demonstrate that QLHH-GA produces solutions comparable to those obtained by the MILP model on small-scale instances and maintains strong solution quality on larger instances, for which exact optimization becomes computationally prohibitive. These findings demonstrate the scalability and effectiveness of reinforcement-learning-guided hyper-heuristic search for designing cost-efficient and ergonomically constrained human–robot collaborative assembly lines. Full article

Residual creases generated during the leather spreading process exhibit highly variable morphologies and irregular feature distributions, causing significant challenges for feature extraction and leading to low localization accuracy. To address these issues, this paper proposes the Dynamic, Cross-Calibrated, and Edge-Enhanced YOLOv8n-Pose (DCE-YOLOv8n-Pose) algorithm. Instead of providing regional approximations, this framework outputs precise spatial coordinates for robotic grasping by integrating three synergistic components in a progressive network flow. First, dynamic snake convolution adaptively perceives the continuous geometric features of elongated creases; subsequently, an efficient multi-scale attention mechanism provides cross-dimensional weight calibration to suppress highly homochromatic background interference and correct spatial misalignments; finally, an edge-enhanced content-aware reassembly of features module preserves high-frequency gradients and prevents feature fracturing during multi-scale fusion. For comprehensive evaluation, a dataset comprising 700 original laboratory images was constructed. To prevent data leakage, the dataset was partitioned into training and validation sets based on individual leather specimens, ensuring that images of the same leather piece do not appear in both sets. Additionally, an independent test set of 500 images collected from an actual processing plant was designed for industrial validation. Experimental results indicate that, at an Intersection over Union (IoU) threshold of 0.5, the DCE-YOLOv8n-Pose model achieves a bounding box mean average precision (mAP@0.5) of 91.8% and a keypoint mAP@0.5 of 85.1%, with a keypoint precision of 87.9%. The computational load is maintained at 9.2 GFLOPs, alongside an inference speed of 114.3 FPS. Furthermore, consistent convergence across four independent training runs substantiates the model’s reliability in reducing missed detection rates and localization deviations. In conclusion, the proposed algorithm demonstrates practical applicability for the visual guidance of automated leather spreading equipment by balancing detection precision and inference speed, thereby offering an effective coordinate reference for subsequent robotic stretching operations. Full article

The increasing use of autonomous mobile robots (AMRs) in internal logistics systems improves operational efficiency. However, it also introduces challenges related to safety, reliability, sensor-based monitoring and human–robot interaction. This study proposes a sensor-driven Digital Twin and fuzzy decision-support framework for operational risk monitoring in AMR-based transportation systems. The proposed approach integrates Digital Twin technology with fuzzy logic methods to support continuous sensing, operational data acquisition, and data-driven risk evaluation in autonomous logistics environments. In the proposed framework, the Digital Twin acts as a continuous monitoring and early-warning environment. It enables continuous observation of system states, robot condition, navigation performance, traffic intensity and operational disturbances. To support decision-making under uncertainty, the fuzzy Analytic Hierarchy Process (fuzzy AHP) is applied to determine the relative importance of selected safety and reliability indicators. These indicators include condition monitoring parameters, mean time between failures, sensor-related disturbances and task completion performance. Subsequently, a hierarchical Mamdani fuzzy inference system is used to evaluate the operational risk level of the transportation system based on aggregated KPI values derived from Digital Twin data. The applicability of the proposed approach is illustrated through a case study involving multiple AMRs operating in a dynamic intralogistics environment. The results indicate that the integration of sensor-based Digital Twin monitoring with fuzzy decision-support mechanisms improves operational risk visibility and supports more effective risk identification and management in Industry 4.0 intralogistics systems. Full article

Reviews of artificial intelligence (AI) for mobile robots usually cover one competence—perception, SLAM, path planning, control, or reinforcement learning—and rarely show how these combine into a working system. We take the opposite view and treat autonomy as one pipeline: sensing, perception, localization and mapping, prediction, planning, visual servoing and control, high-level decision-making, and continual learning. We survey how AI has reshaped each stage for industrial and service robots across Industry 4.0, 5.0, and the emerging Industry 6.0. Using a structured, PRISMA-informed protocol with explicit search strings, inclusion criteria, and cross-embodiment transfer rules, we screen the literature, analyze a corpus drawn mainly from the last five years, and position it against prior surveys with a coverage matrix that exposes their single-block focus. Four findings stand out. Perception and localization approach engineering maturity through multimodal fusion and foundation vision models. Planning and control stay effective but computationally demanding. Decision-making, now driven by large language and vision–language–action models, is powerful yet unverifiable and fails under safety constraints. Lifelong learning is almost absent from deployed systems. The decisive weaknesses sit at the interfaces: at the perception–planning, planning–control, and control–decision handoffs the sim-to-real gap, limited on-robot compute, and scarce industrial data compound. We compare AI families by technology readiness, catalog datasets and benchmarks, examine the safety-certification barrier, and consolidate cross-cutting gaps. We close with a staged roadmap toward Industry 6.0 and a next-generation architecture coupling a foundation perception backbone, a world model and digital twin, a continual-learning memory, and a reasoning core wrapped by a safety monitor. The aim is to move from cataloging algorithms to engineering integrated autonomy. Full article

The increasing complexity of cyber–physical manufacturing systems demands simulation architectures that scale with the physical plant without a proportional growth in engineering effort. This paper introduces a formal, symmetry-based framework for behavioral reuse in arbitrary cyber–physical manufacturing systems, implemented within the Siemens NX Mechatronic Concept Designer (MCD), version NX 2506, environment. Symmetry is treated rigorously, as an equivalence relation induced by a symmetry-group action over the set of plant components, and three exploitable classes are defined on this basis: structural symmetry, arising from replicated kinematic configurations; functional symmetry, arising from shared behavioral specifications across instances of a common component class; and temporal symmetry, arising from synchronized cyclic behavior across concurrent actors. From these definitions, a four-condition behavioral inheritance protocol is derived, specifying the prerequisites under which a single behavioral library template is correctly instantiated across an arbitrary number of interchangeable components. The framework is demonstrated on a production cell comprising ten conveyor sections, nine CNC machining centers (5-axis, X/Y/Z/A/B/SP), and two COMAU NJ420-3.0 manipulators—each a 6-axis articulated arm extended by an external linear rail to seven controlled axes—governed through Siemens Sinumerik RunMyRobot/Direct Control and exercised in a co-simulation environment that integrates a Create MyVirtual Machine (CMVM) Software-in-the-Loop (SiL) controller, a Simit Model-in-the-Loop (MiL) communication layer, and MCD for kinematic and behavioral emulation. Using the number of independent behavioral configuration operations as the effort metric, the symmetry-driven approach reduces machining-center configuration effort by 88.9% (from nine independent configurations to one template instantiated nine times) and robot behavioral configuration effort by 100% (both manipulators inherit from a single seven-axis library entry), while preserving full kinematic and signal-level fidelity. The inheritance mechanism is shown to tolerate heterogeneous kinematic substitution: a COMAU NJ420-3.0 may be replaced by any kinematically equivalent 6-axis manipulator in the RunMyRobot database without behavioral reconfiguration. The component and capability mapping matrix (CCMM) introduced in prior work is extended with a symmetry-annotation layer that explicitly encodes instance relationships and inheritance chains, providing a structured input to automated behavioral-deployment workflows. The results establish symmetry-based modular simulation as a principled and scalable methodology for industrial digital-twin development in multi-robot manufacturing environments. Full article

Background: Population ageing, increasing care demands, and rapid advances in artificial intelligence and robotics have intensified interest in care robots as potential tools to support independent living and complement human caregiving. However, the successful implementation of robotic technologies depends largely on public acceptance, which is influenced by functional, psychological, ethical, cultural, and generational factors. Objective: This study examined generational differences in the acceptance of care robots among Portuguese adults by integrating the Almere Model of technology acceptance with the Katz Index of Activities of Daily Living (ADL) and the Lawton–Brody Instrumental Activities of Daily Living (IADL) Scale. The research sought to determine whether acceptance varies according to generation and the type of caregiving activity performed by the robot. Methods: A cross-sectional quantitative study was conducted using an online questionnaire administered to a purposive sample of 235 adults residing primarily in the Lisbon Metropolitan Area, Portugal. The questionnaire combined constructs from the Almere Model with perceptions of robotic assistance for ADLs and IADLs. Principal Component Analysis, reliability analysis, descriptive statistics, and inferential analyses were performed to examine differences across generational groups. Results: Acceptance of care robots was strongly task-dependent. Participants expressed significantly greater acceptance of robots assisting with instrumental activities, including housekeeping, shopping, transportation, meal preparation, and medication management, than with intimate personal care activities such as bathing, dressing, toileting, feeding, and continence care. Contrary to common assumptions regarding digital natives, Generation Z reported higher levels of fear, discomfort, and perceived intimidation than Generation X and Baby Boomers. Older generations generally demonstrated more pragmatic acceptance of robotic assistance, particularly regarding future support needs associated with ageing. Across generations, respondents preferred robots with more human-like appearances; however, emotional trust remained substantially lower than perceived functional usefulness. Conclusions: The findings suggest that acceptance of care robots is conditional rather than universal and is shaped by the nature of the caregiving task, generational differences, and broader emotional and cultural perceptions of care. Integrating the Almere Model with established ADL and IADL frameworks provides a novel perspective by linking technology acceptance to specific functional domains of caregiving. The results support the view that care robots are more likely to be accepted as complementary tools that enhance human-centred care rather than as substitutes for professional or family caregivers. Given the purposive and geographically limited sample, the findings should be interpreted cautiously and not generalised to the wider Portuguese population. They nevertheless provide valuable implications for the design of socially assistive robots, healthcare practice, and public policy in ageing societies. Full article

Copper and its alloys are indispensable for electronics, communications, new energy systems, and aerospace engineering due to their exceptional electrical conductivity and mechanical properties. However, the thin cuprous oxide (Cu₂O) layer that naturally forms on copper and its alloys is prone to failure under elevated temperatures and high humidity, particularly in chloride-rich environments, leading to accelerated localized corrosion. While conventional chromate-based passivation has long been the industrial standard for preventing corrosion, its use has been increasingly restricted by global regulations (such as RoHS and REACH) due to its severe toxicity and health risks. To address the conflict between environmental compliance and protective performance, this review systematically evaluates recent advances in environmentally friendly, chromium-free anti-corrosion coatings in the present review. These alternative coatings are critically analyzed and categorized into four mechanistic groups: (i) inorganic conversion coatings (including molybdate, tungstate, rare earth, and phosphate systems); (ii) organic films formed via chemical or physical adsorption (such as organic inhibitors, thiol-based monolayers, and organosilane self-assembled films); (iii) conversion coatings engineered through covalent bonding, coordination chemistry, and microstructural tailoring; and (iv) multifunctional coatings that integrate self-healing capability with high electrical conductivity. Beyond providing a technical summary, this review explored how the swift progression of electronic information technology, new energy infrastructure, and robotics has imposed more exacting, multifunctional demands on copper components. This review provides a strategic roadmap for future research and prioritizes the creation of protection strategies that operate robustly in multi-physics coupling environments—integrating high conductivity, autonomous self-healing, and long-term chemical stability to ensure the reliability of next-generation infrastructure. Full article

To address the difficulty of simultaneously optimizing execution time, energy consumption, and motion smoothness for six-degrees-of-freedom (6-DOF) industrial robotic manipulators in continuous operations such as high-speed handling and assembly, this study proposes a multi-objective joint-space trajectory optimization method based on an improved Dung Beetle Optimizer (IDBO). First, to adapt DBO to constrained multi-objective trajectory optimization, an external archive, nondominated sorting, and a crowding distance mechanism were incorporated to construct and maintain the Pareto solution set. Second, Sobol low-discrepancy sequence initialization was used to improve the initial population distribution. Adaptive Lévy flight perturbation and an adaptive random perturbation mutation strategy for non-elite individuals were further combined to enhance global exploration and reduce the risk of premature convergence. Finally, seventh-degree B-spline curves were adopted to construct a continuous joint-space trajectory model. Based on this model, a multi-objective trajectory optimization model was established by considering total execution time, energy consumption, and jerk as the optimization objectives. Furthermore, simulation experiments were conducted using MATLAB R2024a, and the proposed algorithm was compared with multi-objective particle swarm optimization (MOPSO), an improved multi-objective differential evolution algorithm (GMODE), the nondominated sorting genetic algorithm II (NSGA-II), and the multi-objective Dung Beetle Optimizer (MODBO). The results showed that the proposed algorithm obtained a Pareto front with better convergence, wider coverage, and a more uniform distribution. Compared with MOPSO, GMODE, NSGA-II, and MODBO, the mean hypervolume (HV) obtained by IDBO was 13.24%, 8.43%, 2.29%, and 2.34% higher, respectively; the mean inverted generational distance (IGD) was 9.45%, 26.68%, 16.35%, and 11.05% lower, respectively; and the mean Spacing value was 55.09%, 64.81%, 58.95%, and 14.06% lower, respectively. The execution time, energy consumption index, and joint jerk of the selected compromise solution were 5.27 s, 2.48, and 9.79, respectively, which were 29.73%, 43.51%, and 18.14% lower than those of the unoptimized trajectory. Constraint verification showed that the peak joint velocities, accelerations, and jerks remained within their prescribed limits. These results indicate that the proposed method provides a feasible approach for multi-objective joint-space trajectory planning of industrial robotic manipulators. Full article

Curves constructed directly on point clouds are a core primitive in reverse engineering, product design, and point-based CAD; many workflows additionally require the curve to lie in a plane—e.g., as a section profile, inspection path, or design reference. This paper presents an algorithmic framework for computing free and plane-constrained geodesic curves directly on oriented point clouds, without any intermediate surface or mesh reconstruction. A geodesic-curvature-minimizing solver that combines a Newton/conjugate-gradient flow with directed projection, elliptic Gabriel neighborhoods, and Taubin smoothing forms the backbone; the plane-constrained problem is then reduced to a one-parameter pencil of planes through the endpoint chord and solved per plane by alternating projection onto the cloud and the plane, with a projection-only pre-lift and a penalized length objective that rejects sections floating off the cloud; the returned section is the best found over a sampled pencil of candidate planes. The returned sections are attached to the cloud within a small fraction of the mean sampling distance. All algorithms are given in pseudocode with convergence criteria and complexity estimates. Two parallel realizations of the plane search are developed and measured: a multithreaded CPU backend (about 3× over the serial scan) and a WebGPU backend that evaluates the whole plane pencil in a single compute dispatch. Accuracy is validated against the analytic conic sections of a cone and against cylinder and sphere benchmarks whose optimal plane is known in closed form; robustness is assessed under noise, non-uniform sampling, missing regions, outliers, and perturbed normals, and against both a slab-projection baseline and the conventional reconstruct-then-slice route. Five applications—shoe-last reverse engineering with a C² surface reconstruction, anthropometric girth measurement, medical transverse sectioning, dimensional metrology on industrial mold scans, and cleaning-path planning for a robotic surface-treatment task—demonstrate the plane-constrained geodesic curves in practice. Full article

When implementing collaborative robot applications, it is paramount to use a human-centered development approach to ensure a positive user experience and increase acceptance. User Experience (UX) design methods involve validating user experience through evaluations as a basic principle. The earlier UX evaluations are carried out, the greater the added value that can be achieved. For collaborative robot applications, especially those involving large robot systems, these early evaluations are challenging since the entire application will not be available until the final stages of development. The proposed methodological approach to this problem utilizes a rudimentary, scaled test setup for early UX evaluations of the entire robot application, enabling user feedback to be incorporated into the development process early on. The method was applied in a project that developed a collaborative robot application for semi-automated liquid cargo handling in inland navigation. UX assessments were carried out using both the rudimentary test setup and a full-scale prototype in a later development phase. The comparison of both assessments proves the applicability of the proposed methodology. Serving as an overarching framework, this methodology encourages developers to test the entire collaborative robot application in user studies at an early stage, thereby gathering valuable user feedback. Full article