Automation

Reliable communication infrastructure is a fundamental component of Intelligent Transport Systems (ITSs), particularly in scenarios involving maritime corridors and emergency traffic management. In locations where optical fiber deployment is geographically constrained, unmanned aerial vehicle (UAV)-assisted free-space optical (FSO) relay links provide a flexible and rapidly deployable alternative. However, atmospheric attenuation, turbulence-induced fading, and wind-induced UAV misalignment can severely degrade link reliability and disrupt real-time transport data streams. This study proposes a payload-efficient multiple-input multiple-output free-space optical (MIMO-FSO) relay architecture based on a multi-output/single-input (MOSI) uplink and a single-output/multi-input (SOMI) downlink. Here, MOSI denotes multiple ground-based transmit apertures directed toward a single UAV receiving aperture, whereas SOMI denotes one UAV transmitting aperture serving multiple ground-based receiving apertures. Unlike conventional symmetric UAV-assisted MIMO-FSO relays that may duplicate diversity hardware on the aerial node, the proposed design shifts the parallel optical branches to the ground stations and keeps only one optical receiver and one optical transmitter on board the UAV. Under the adopted 4 × 4 comparison assumption, this reduces the UAV-side optical branch count from eight to two, corresponding to a 75% branch-count reduction proxy. System performance is evaluated over a 1.54 km relay link. The analytical framework describes Beer–Lambert attenuation, log-normal/gamma–gamma turbulence, and statistical pointing errors; in the OptiSystem implementation, their combined effects are represented by equivalent aggregate losses of 25 dB/km for atmospheric absorption/scattering and 25.5 dB/km for turbulence- and pointing-related degradation. Comparative simulations for SISO, 2 × 2, and 4 × 4 configurations show that the proposed 4 × 4 architecture increases the Q-factor from 8.38 to 18.25 and changes the OptiSystem-reported minimum BER from 2.73 × 10⁻¹⁷ to 9.95 × 10⁻⁷⁵. Because a finite simulation cannot statistically validate error probabilities of this magnitude through raw error counting, values far below 10⁻¹² are interpreted primarily as comparative indicators of receiver decision margin. The findings provide simulation-based evidence that the proposed architecture is a scalable candidate for resilient optical wireless backhaul in smart transport corridors under adverse propagation conditions. Full article

This paper presents a single-company field study on hybrid user memory filtering for Large Language Model (LLM)-based knowledge management systems, aiming to reduce contextual noise from irrelevant or outdated persistent memories. We propose the Hybrid Adaptive Filtering Engine (HAFE), which combines intent classification, ontology-based filtering, behavioral reuse prediction, and collaborative role-level comparison. HAFE was integrated into an industrial KM platform deployed at a major steel producer. In a field experiment with 120 engineers, HAFE reduced irrelevant memory retention by 41%, improved Mean Reciprocal Rank (MRR) by 12.5%, and increased user satisfaction (SUS score) by 18% (all p < 0.01). The results suggest that proactive memory quality control can improve effectiveness and user experience in this specific industrial KMS setting, while further cross-domain validation is required. Full article

Manned–unmanned teaming (MUMT) represents a critical evolution in collaborative operations across domains including search and rescue, firefighting, surveillance, and defense. Despite widespread interest in MUMT capabilities, the field lacks a unified taxonomy for classifying and comparing system capabilities, hindering systematic development and technology integration. This paper presents a comprehensive framework for MUMT that addresses the fundamental challenge of organizing and assessing cognitive agent capabilities within human–machine teams. Building upon established automation frameworks, we propose a three-dimensional framework comprising information analysis and inference, decision-making, and action execution. Each dimension defines six hierarchical levels of teaming, ranging from human-only operations to fully autonomous cognitive agent capabilities. The framework distinguishes itself from existing taxonomies by explicitly modeling collaborative teaming rather than simple task delegation, incorporating transparency requirements, and addressing dynamic authority relationships between humans and cognitive agents. The proposed taxonomy provides researchers and engineers with a common vocabulary for MUMT development, enables gap analysis for technology roadmaps, and facilitates the identification of integration opportunities across organizational boundaries. Full article

In the context of industrial digitalization and the widespread adoption of process automation systems, Knowledge Management Systems (KMS) play a key role in providing operational personnel with up-to-date instructions and regulations. However, the inherent ambiguity of natural language in technical documentation remains a serious obstacle, leading to incorrect operator actions, process deviations, and increased safety risks. This article investigates the integration of Large Language Models (LLMs) into KMS and its impact on user experience and human–machine interaction in industrial automation environments. A method called Semantic Latent Choice Detection is presented, designed to systematically identify interpretation ambiguities in process instructions and operator commands. Unlike existing approaches that require access to the internal model architecture (“white box”) or token-level logits, the proposed method is logit-free and operates with closed commercial LLMs (“black box”) via standard API interfaces. The method analyzes the semantic similarity of binary text blocks and polysemous terms within the context of a specific technological process. Using a metallurgical production case study, we demonstrate how the system detects hidden semantic collisions (e.g., the difference between “adding ferroalloys into the ladle” and “feeding ferroalloys onto the conveyor”) that are missed by traditional rule-based validation methods. Instead of arbitrarily selecting an interpretation, the system initiates a clarification request to the human operator, thereby reducing cognitive load, preventing erroneous automated decisions, and increasing trust in the KMS. An empirical evaluation conducted in a real-world industrial setting (unit control rooms and dispatch centers) shows a statistically significant reduction in errors related to misinterpretation of process regulations. The article contributes to the fields of automation engineering, knowledge management, and human-centered automation by proposing a novel method for validating operational instructions in high-risk industrial environments. Full article

Engineer-to-Order (ETO) manufacturing environments are characterized by high product variety, low repetitiveness, and unstable demand, which pose significant challenges to the application of Lean Manufacturing (LM). This study investigates the application and adaptation of LM principles and tools in an ETO production line using an action research approach integrated with Value Stream Mapping (VSM). The research was conducted at a manufacturer of highly customized electrical equipment. An adapted method for calculating representative cycle times based on weighted production volumes was developed to support line sizing and workload balancing. The proposed future-state design incorporates multifunctional operators, FIFO lanes, daily scheduling, and pitch-based control. The results show a 9.5% reduction in labor requirements, a 61.7% decrease in manufacturing lead time, and a 75.0% reduction in overtime hours. Statistical validation using daily PPC records confirmed significant improvements in actual output, schedule adherence, overtime, and lead time after implementation. In addition to operational improvements, this study offers methodological contributions by proposing practical adaptations of LM tools suitable for high-variability ETO environments, thereby contributing to both theory and industrial practice. Full article

The control of Dual-Star Induction Machines (DSIMs) with high performance remains a challenging task, particularly in the presence of parameter variations and under sensorless operation. In practice, widely used controllers such as Proportional–Integral (PI) and classical sliding mode (SM) often reach their limits, especially in terms of dynamic responses, sensitivity to disturbances, and chattering, which can negatively affect system stability and efficiency. In this work, an improved Rotor Flux-Oriented Control (RFOC) strategy is proposed. It combines a super-twisting sliding mode (STSM) speed controller with a Model Reference Adaptive System (MRAS) observer. The STSM controller ensures faster convergence and enhanced robustness while significantly reducing chattering. Meanwhile, the MRAS observer enables accurate rotor speed estimation without mechanical sensors, thereby simplifying the system and improving reliability. The control scheme is developed using the Xilinx System Generator (XSG) in a fixed-point environment, providing an FPGA-oriented and compatible simulation framework. To assess its effectiveness, the proposed method is evaluated through several simulation scenarios and compared with conventional RFOC-PI and RFOC-SM approaches. The results demonstrate clear improvements in dynamic performance, disturbance rejection capability, and steady-state accuracy. Overall, the proposed approach provides a practical and efficient solution for DSIM drive systems operating under demanding conditions. Full article

Learning-based approaches have significantly advanced the capabilities of Simultaneous Localization and Mapping (SLAM) systems, particularly in challenging environments characterized by noise, dynamic objects, and perceptual ambiguity. However, the literature remains highly heterogeneous in terms of sensing modalities, datasets, evaluation protocols, and reporting practices, making systematic comparison difficult. This paper presents a taxonomy-driven review of learning-based SLAM approaches, with particular emphasis on LiDAR-based systems in mobile robotics, and introduces a functional taxonomy that categorizes methods according to the role of learning within the SLAM architecture: (i) learning-enhanced front-end SLAM (T1), (ii) learning-enhanced back-end SLAM (T2), and (iii) learning-centric SLAM systems (T3). Representative studies were analyzed with respect to performance characteristics, robustness, computational requirements, datasets, and deployment-related evidence. The analysis shows that T1 approaches primarily improve local pose estimation and robustness, T2 methods enhance global consistency through learning-based loop closure and relocalization, and T3 approaches explore unified representations, semantic reasoning, and learning-centric autonomy, albeit with greater computational demands and limited deployment evidence. The review further indicates that hybrid approaches combining geometric and learning-based components constitute a prominent trend in the literature, frequently reporting improvements in accuracy and adaptability while maintaining compatibility with established SLAM frameworks. Nevertheless, these observations should be interpreted cautiously, as stronger empirical evidence for hybrid systems may partially reflect their greater technological maturity and broader evaluation history. Finally, the review identifies persistent challenges, including limited cross-domain generalization, high computational requirements, limited deployment-oriented evaluation, and the lack of standardized benchmarking and reporting practices. These findings highlight the need for more reproducible evaluation methodologies, uncertainty-aware learning strategies, and computationally efficient architectures for robust real-world autonomous SLAM. Full article

A common limitation of existing multi-AGV cooperative systems is their reliance on the obstacle-agnostic Manhattan distance as the basis for reward signals. This causes agents to receive misleading feedback, engage in excessive futile exploration, and ultimately achieve poor training quality. To address this, we introduce an A*-distance guidance mechanism for multi-agent reinforcement learning (MARL) path planning, built on the precise path distance computed via the A* algorithm (A*-distance). Within the QMIX framework, we incorporate an A*-distance-based guiding function into the action selection mechanism. This function evaluates candidate actions by quantifying their immediate effect on the A*-distance, providing positive incentives for actions that bring the agent closer to the goal and applying negative penalties for those that lead it farther away. This effectively biases exploration towards actions that genuinely shorten the obstacle-aware path to the goal, suppresses ineffective exploration, and accelerates policy convergence. Experiments in four warehouse environments (simple obstacles, complex obstacles, large-scale, and congested) show that, compared with standard QMIX, the proposed method achieves higher global average reward and faster convergence. The advantage grows as environment scale and obstacle density increase. In the large-scale and congested environments, standard QMIX and the other MARL baselines fail to solve the task, whereas the proposed method still succeeds. It is the only learning-based method to solve these hardest tasks while keeping path length close to that of dedicated search-based solvers. Ablation experiments further show that the A*-distance-guided action selection is the primary contributor to these gains, while the A*-distance reward plays a supporting role. Full article

This paper proposes a genetic algorithm (GA) for the Dual-Resource Flexible Job Shop Scheduling Problem with Partial Resource Allocation (DRFJSSP-PRA), a particular variant of a dual-resource constrained scheduling problem that has not been fully explored due to its intricate nature. The DRFJSSP-PRA poses a challenging scheduling problem, having several applications in many industries, including food, chemistry and pharmaceutics. The proposed algorithm is applied to real-world scheduling instances in pharmaceutical quality control. The objective function considered is the total completion time. The GA is compared with three state-of-the-art algorithms. For small- and medium-size instances, the proposed algorithm achieves optimal or near optimal results for the majority of the instances tested. For large-sized instances, the proposed GA outperforms all the other algorithms, in all of the tested instances. Thus, the experimental results show that the proposed GA achieves competitive results for any type of instance. The proposed algorithm also has the ability to optimize production processes through scheduling, leading to potential cost savings, increased efficiency, and improved competitiveness. Full article

Liquid storage tanks are widely used in sectors such as water treatment, oil and gas, food processing, and chemical manufacturing. Knowing the exact amount of liquid in a tank is essential for ensuring safety, preventing spills, and optimizing process control; therefore, the liquid level in a tank must be maintained at a precise reference point. This is where liquid level control for tanks becomes crucial and constitutes a fundamental problem in the industrial sector due to nonlinearities, multivariable coupling, and stochastic disturbances. Given the drawbacks of available control methods, such as classical Model Predictive Control (MPC), which are highly dependent on model accuracy and struggle to reject complex stochastic noise, predicting random disturbances represents a major technological challenge. A new approach is proposed to specifically address the problem and challenge of the four-tank system, where water levels in two lower tanks must be controlled by two pumps, often with varying delays and significant parameter disturbances. To establish a relationship between expected performance and MPC parameters, this approach uses a novel hybrid nonlinear MPC, Extended State Observer, and Physics-Informed Neural State Estimation (NMPC-ESO-PINSE) architecture. A Physics-Informed Neural State Estimation (PINSE) layer, chosen for its learning capacity, is designed to filter sensor noise by applying Bernoulli’s physical laws, while an Extended State Observer (ESO) is integrated to capture and compensate for unmodeled uncertainties in the process. Finally, a proposed hybrid (NMPC-ESO-PINSE) strategy leverages these clean, physically consistent state estimations to solve a non-convex optimization problem via Sequential Quadratic Programming (SQP), computing optimal pump voltages. Extensive numerical simulations demonstrate the superior resilience of this decoupled framework against parametric drifts and continuous noise sequences, yielding a $+27.36\%$ reduction in global Root Mean Square Error (RMSE) compared to standard NMPC, accelerating the closed-loop settling time to $15.2 \mathrm{s}$, and restricting transient overshoot to just $0.18\%$. Full article

This paper focuses on state estimation for nonlinear stochastic systems with multiple switching models, especially under challenging conditions where the model dynamics are unknown and the transition probability matrix is uniformly distributed. Gaussian process regression is employed to learn the unknown system dynamics from an offline discrete dataset and is integrated into an interacting multiple model particle filtering framework. GPR enables data-driven learning of both state transition and observation functions. To cope with model uncertainty and uninformative prior transition knowledge, particularly under uniformly initialized TPM, a dual-layer adaptive TPM update strategy based on hidden Markov model inference is further incorporated. Finally, the proposed method is validated through simulations and compared with IMMPF under different assumptions on system dynamics and TPMs. The results show that, even without prior knowledge of the system dynamics or precise TPM information, the proposed GP-AIMMPF maintains robust and accurate state estimation performance. Full article

AI-enabled cyber–physical systems (CPSs) are increasingly deployed in public governance contexts where they sense human populations, infer classifications or risks, and trigger interventions that can shape liberty, equality, and access to essential services. In these deployments, governance failures often arise not only from model error but from systems-level interactions across data generation, model updates, organizational practices, and downstream actuation. This paper introduces a Risk–Rights–Rules (3R) architecture that treats fundamental rights and legal rules as enforceable constraints on the sensing–inference–actuation loop, rather than as external ethical aspirations. Building on established risk-management baselines and safety engineering practice, we specify a testable assurance object, a structured 3R assurance case, that links rights claims to explicit assumptions, measurable evidence, and accountable control points across the lifecycle. The approach is designed to reduce “legitimacy drift” in stochastic decision pipelines by making uncertainty, demographic error, contestability, and procurement leverage auditable at the system level. The result is a governance blueprint for high-consequence public-sector AI deployments for governance failures, which is both technically robust and institutionally defensible. Full article

Background/Objective: Autonomous vehicles (AVs) require control algorithms capable of handling complex and dynamic environments while satisfying multiple conflicting objectives such as safety, comfort, energy efficiency, and trajectory accuracy. Model predictive control (MPC) offers a principled framework for multi-constraint optimization, yet its real-time feasibility remains challenging for nonlinear vehicle dynamics. Methods: This paper presents a feedforward neural network (FNN)-based MPC framework for autonomous vehicle trajectory tracking. The FNN approximates the coupled vehicle dynamics and visual preview error model using an algebraic sum of log-sigmoid functions. Three adaptive FNN parameter sets, namely, the scaling factor, convergence parameter, and time-shifting parameter, are jointly optimized using a hybrid algorithm that combines the global search capability of fractional particle swarm optimization (FPSO) with the local refinement of sequential quadratic programming (SQP). Results: Comprehensive scenario-based simulations are performed to evaluate trajectory tracking dynamics under dry conditions with an adhesion coefficient of 0.8 and a vehicle mass of 1723 kg moving at a speed of 80 km/h. The results are quantitatively compared with a traditional PID controller and a structurally comparable MPC framework from the literature under identical simulation conditions; related DRL- and RL-based methods are discussed qualitatively for contextual orientation only. The stability, reliability, and computational complexity of the proposed framework are examined based on the mean square error, fitness value, and computational budget in GFLOPs for 100 independent runs. Conclusions: The proposed FNN-based MPC framework demonstrates improved tracking accuracy and optimizer reliability in simulation. While the present results indicate promising computational behavior, real-time deployment will require further validation on embedded automotive hardware and under closed-loop real-time constraints. Full article

Environmental monitoring in hazardous indoor zones conventionally relies on fixed-sensor networks or manual inspections, both of which suffer from spatial blind spots and increased human exposure risks. This paper addresses the problem of transforming sparse, mobile sensor measurements into spatially resolved risk assessments in GPS-denied environments. We propose a Hazard Index (HI) framework that normalizes environmental parameters against established safety thresholds into a unified, graduated risk metric with $O\left(N\right)$ computational complexity, where N is the number of monitored parameters. The framework is designed for multi-parameter hazard assessment; the present work validates the computational pipeline, spatial mapping methodology, and classification logic through single-parameter CO₂ detection ($N=1$) deployed on a LiDAR-guided robotic platform integrating an MQ-135 gas sensor interfaced via a NodeMCU ESP8266 microcontroller. Experimental validation across a 144 sq ft indoor area achieved a trajectory-following RMSE of 0.54 ft relative to planned waypoints using Hector SLAM without odometry, detected CO₂ concentrations ranging from 0.02% to 0.25%, and identified a hazardous region encompassing eight measurement points ($\mathrm{HI}\ge 1.0$) using a three-tier classification scheme (Safe, Elevated, Hazardous) within 225 s of active mapping. The framework provides a lightweight computational footprint suitable for real-time evaluation on an NVIDIA Jetson Nano. The proposed approach establishes a cost-effective, reproducible methodology for autonomous indoor environmental monitoring, with the modular architecture designed for future expansion to multi-parameter sensing. Full article

Firefighter training requires accurate posture monitoring to reduce injuries and improve performance assessment, yet traditional tracking methods suffer from high occlusion rates and the uniform appearance of trainees. To address these challenges, we propose an improved multi-target tracking algorithm that integrates YOLOX for detection, BlazePose for posture estimation, and a pose-constrained extension of DeepSORT. First, posture features are introduced into the association metric through a posture-cosine distance, which enhances discrimination between visually similar firefighters. Second, a pose-guided bounding-box correction is applied to ensure complete coverage of the human body region, improving the quality of extracted posture information. Experiments were conducted on a custom firefighter training dataset comprising 6602 labeled images and five multi-target video sequences (FM-1 to FM-5). The proposed method achieved a mean Average Precision (mAP) of 97.8% for detection and improved tracking performance compared to baseline DeepSORT, with MOTA rising from 74.72% to 82.96% and IDF1 from 74.77% to 82.36%. These results demonstrate that the algorithm effectively handles severe occlusion and appearance similarity, providing a reliable tool for posture tracking and behavior perception in firefighter training environments. Full article

This paper investigates uncertainty-resilient stabilization of an inverted pendulum on a cart (IPOC) using an interval type-2 Takagi–Sugeno (IT2 T–S) fuzzy model and an LQR-based control framework. The IPOC dynamics are represented as a weighted combination of local linear subsystems, where interval firing strengths derived from upper and lower membership functions capture modeling uncertainties. An LQR state-feedback controller is designed for each subsystem, and the final control input is obtained by blending the local controllers according to the normalized firing strengths. To analyze stability, an LMI-based verification condition is established as a sufficient condition for the subsystem LQR controllers. Simulation results show that this condition is satisfied only in a limited operating region, while the closed-loop system can still remain stable even when the condition is violated, demonstrating the reduced conservatism and flexibility of the proposed approach. Furthermore, comparisons with the conventional PDC structure confirm that the proposed method provides greater design flexibility and enables a trade-off between robustness and transient-state performance. Full article

This paper proposes a reinforcement learning-assisted active disturbance rejection control (ADRC) framework for a nonlinear quadrotor unmanned aerial vehicle (UAV). Conventional ADRC controllers are designed for the quadrotor altitude and attitude channels. To evaluate robustness under disturbance-intensive conditions, a composite external disturbance is injected into the roll-channel dynamics. A Deep Deterministic Policy Gradient (DDPG)-based adaptive tuning mechanism is integrated into the roll-channel ADRC for the nonlinear state error feedback (NLSEF) gain adaptation, while fixed-parameter ADRC is retained for the remaining three channels. Without requiring system linearization and prior knowledge of disturbance models, the reinforcement learning agent learns an optimal gain adaptation policy directly through interaction with the nonlinear roll subsystem. Quantitative simulations demonstrate superior roll-axis disturbance rejection, leading to 90% faster settling time, the root mean square (RMS) control effort being reduced by 5.1%, and a 7.6% peak input suppression compared to conventional ADRC. The learning-based adaptation maintains comparable tracking accuracy across all channels while significantly improving transient recovery and control smoothness in the most disturbance-sensitive axis, validating selective reinforcement learning integration for robust nonlinear quadrotor flight control. Full article

Modern distribution networks increasingly face operational stress from variable demand and high penetration of distributed energy resources, challenging the adequacy of purely reactive protection schemes. This study addresses this challenge by enhancing a developed adaptive protection software platform with a Geographic Information System (GIS) driven predictive load forecasting capability to enable anticipatory protection coordination. The proposed framework integrates spatially resolved demand modeling, regulatory and planning constraints, and machine learning-based short- to medium-term load forecasting with a relay coordination and optimization engine. Forecasted load profiles are used as inputs to an optimization layer that proactively updates relay pickup and time delay settings to maintain selectivity and system security under predicted operating conditions. The approach is validated at laboratory scale using real Intelligent Electronic Devices (IEDs) interfaced with synthetic GIS-based network and load datasets. Experimental results indicate that incorporating forecast-informed settings improves coordination margins and reduces the risk of relay maloperation compared with reactive adaptive protection alone. The findings demonstrate that coupling GIS based constrained load forecasting with adaptive relay control can enhance protection performance in active distribution networks, supporting more resilient and forward-looking protection strategies. Full article

In the paper, a systematic treatment of sensitivity analysis of multivariable cont rol systems within the framework of the characteristic transfer functions (CTFs) method is given. The CTFs method (also called characteristic gain loci method) allows one to associate with an N-dimensional multi-input multi-output (MIMO) system a set of N independent single-input single-output (SISO) characteristic systems and thereby to reduce the analysis and design of a MIMO system to the analysis and design of N SISO systems. The formulas determining the sensitivity functions of the CTFs and the sensitivity vectors of the canonical basis axes to small variations of parameters of general type MIMO systems are derived. The relations between the sensitivity functions of the open-loop and closed-loop MIMO systems are established. Two illustrative examples are considered. The first of them concerns the sensitivity of a two-dimensional non-robust system with a large degree of skewness of the canonical basis axes. In the second example, the sensitivity of the control system of a hexacopter (a multirotor UAV with six rotors) to small degradations in motors efficiency is analyzed. Full article