Industry 5.0 is driving a new era in industrial automation, where the collaboration between artificial intelligence (AI) and human supervision enables the development of smarter, more adaptive, and more efficient systems. Robotic trajectory generation is a clear example of this new paradigm. Metaheuristic techniques help automatically generate optimized trajectories, thereby improving operational efficiency. However, optimizing trajectories using AI alone also presents limitations. Starting from random trajectories, the optimization process becomes computationally expensive, especially in complex environments. In this context, initial input from human experts plays a crucial role: expert-defined trajectories provide structured, feasible, and contextual starting points that guide AI more effectively toward high-quality solutions. Therefore, this work proposes a novel human-guided trajectory optimization algorithm. In this way, human knowledge, Particle Swarm Optimization (PSO), and Pattern Search (PS) are efficiently combined. The results demonstrate that this approach significantly improves robotic system performance, achieving cycle time reductions of up to 16.69% compared to expert-defined trajectories. This approach establishes a solid framework for intelligent automation in Industry 5.0, promoting the development of more efficient, sustainable, and adaptive robotic systems.

ABSTRACT In the context of industrial automation, optimising automated guided vehicle (AGV) trajectories is crucial for enhancing operational efficiency and safety. They must travel in crowded work areas and cross narrow corridors with strict safety and time requirements. Bio‐inspired optimization algorithms have emerged as a promising approach to deal with complex optimization scenarios. Thus, this paper explores the ability of three novel bio‐inspired algorithms: the Bat Algorithm (BA), the Whale Optimization Algorithm (WOA) and the Gazelle Optimization Algorithm (GOA); to optimise the AGV path planning in complex environments. To do it, a new optimization strategy is described: the AGV trajectory is based on clothoid curves and a specialised piece‐wise fitness function which prioritises safety and efficiency is designed. Simulation experiments were conducted across different occupancy maps to evaluate the performance of each algorithm. WOA demonstrates faster optimization providing suitable safety solutions 4 times faster than GOA. Meanwhile, GOA gives solutions with better safety metrics but demands more computational time. The study highlights the potential of bio‐inspired approaches for AGV trajectory optimisation and suggests avenues for future research, including hybrid algorithm development.

This paper presents an offline optimization method designed for use with industrial robots in environments with static obstacles. It is particularly useful in industry where stability and predictability are crucial to meeting expected timelines in automated guided vehicle operations. The main methodological contribution of this work lies in the integral process used to define an effective fitness function that guides the optimization method in the search for optimal solutions. This cost function plays a critical role in the effectiveness of the trajectory tracking algorithm by quantifying path quality and allowing comparisons between solutions. The design of this fitness function poses challenges including accuracy, suitability, minimization of path length, and avoiding or reducing collisions. To achieve the optimization objectives and address some issues such as sensitivity to parameter scaling and the risk of premature convergence, different approaches can be used. This work proposes to incorporate constraints into the fitness function, adjust the optimization parameters to reflect the conditions of the problem, and design a fitness function based on prior knowledge and an accurate representation of the goals. The three relevant contributions for the planning and optimization of routes of automated guided vehicle in industrial environments are the following. Firstly, the development of a mathematical model of trajectories based on Frenet curves that considers the static occupancy map of the environment. Second, an optimization strategy to generate optimal safe paths. Finally, a fitness function that guides the optimization method towards optimal solutions considering the sensitivity to scaling and resolution of the parameters. This study presents an exhaustive analysis of the different fitness functions obtained, each one evaluated based on key metrics such as the length of the trajectory, the average and minimum distance to the occupancy map, and the number of collisions along the path. The results show that the obtained cost function successfully avoids collisions with the environment in all scenarios and consistently remains the fitness function with the largest average distance to obstacles, at least 50% higher than other functions used in this study.

Abstract With the rapid growth of logistics transportation in the framework of Industry 4.0, automated guided vehicle (AGV) technologies have developed speedily. These systems present two coupled control problems: the control of the longitudinal velocity, essential to ensure the application requirements such as throughput and tag time, and the trajectory tracking control, necessary to ensure the proper accuracy in loading and unloading manoeuvres. When the paths are very short or have abrupt changes, the kinematic constraints play a restrictive role, and the tracking control becomes more challenging. In this case, advanced control strategies such as those based on intelligent techniques, including machine learning (ML) can be useful. Hence, in this work, we present an intelligent hybrid control scheme that combines reinforcement learning‐based control (RLC) with conventional PI regulators to face both control problems simultaneously. On the one hand, PIs are used to control the speed of each wheel. On the other hand, the input reference of these regulators is calculated by the RLC in order to reduce the guiding error of the path tracking and to maintain the longitudinal speed. The latter is compared with a PID path following controller. The PID regulators have been tuned by genetic algorithms. The RLC allows the vehicle to learn how to improve the trajectory tracking in an adaptive way and thus, the AGV can face disturbances or unknown physical system parameters that may change due to friction and degradation of AGV mechanical components. Extensive simulation experiments of the proposed intelligent control strategy on a hybrid tricycle and differential AGV model, that considers the kinematics and the dynamics of the vehicle, prove the efficiency of the approach when following different demanding trajectories. The performance of the RL tracking controller in comparison with the optimized PID gives errors around 70% smaller, and the average maximum error is also 48% lower.

Under the federated learning paradigm, the agents learn in parallel and combine their knowledge to build a global knowledge model. This new machine learning strategy increases privacy and reduces communication costs, some benefits that can be very useful for industry applications deployed in the edge. Automatic Guided Vehicles (AGVs) can take advantage of this approach since they can be considered intelligent agents, operate in fleets, and are normally managed by a central system that can run in the edge and handles the knowledge of each of them to obtain a global emerging behavioral model. Furthermore, this idea can be combined with the concept of reinforcement learning (RL). This way, the AGVs can interact with the system to learn according to the policy implemented by the RL algorithm in order to follow specified routes, and send their findings to the main system. The centralized system collects this information in a group policy to turn it over to the AGVs. In this work, a novel Federated Discrete Reinforcement Learning (FDRL) approach is implemented to control the trajectories of a fleet of AGVs. Each industrial AGV runs the modules that correspond to an RL system: a state estimator, a rewards calculator, an action selector, and a policy update algorithm. AGVs share their policy variation with the federated server, which combines them into a group policy with a learning aggregation function. To validate the proposal, simulation results of the FDRL control for five hybrid tricycle-differential AGVs and four different trajectories (ellipse, lemniscate, octagon, and a closed 16-polyline) have been obtained and compared with a Proportional Integral Derivative (PID) controller optimized with genetic algorithms. The intelligent control approach shows an average improvement of 78% in mean absolute error, 75% in root mean square error, and 73% in terms of standard deviation. It has been shown that this approach also accelerates the learning up to a 50 % depending on the trajectory, with an average of 36% speed up while allowing precise tracking. The suggested federated-learning based technique outperforms an optimized fuzzy logic controller (FLC) for all of the measured trajectories as well. In addition, different learning aggregation functions have been proposed and evaluated. The influence of the number of vehicles (from 2 to 10) on the path following performance and on network transmission has been analyzed too.

Abstract A novel AGV (Automated Guided Vehicle) control architecture has recently been proposed where the AGV is controlled remotely by a virtual Programmable Logic Controller (PLC), which is deployed on a Multi-access Edge Computing (MEC) platform and connected to the AGV via a radio link in a 5G network. In this scenario, we leverage advanced deep learning techniques based on ensembles of N-BEATS (state-of-the-art in time-series forecasting) to build predictive models that can anticipate the deviation of the AGV’s trajectory even when network perturbations appear. Therefore, corrective maneuvers, such as stopping the AGV, can be performed in advance to avoid potentially harmful situations. The main contribution of this work is an innovative application of the N-BEATS architecture for AGV deviation prediction using sequence-to-sequence modeling. This novel approach allows for a flexible adaptation of the forecast horizon to the AGV operator’s current needs, without the need for model retraining or sacrificing performance. As a second contribution, we extend the N-BEATS architecture to incorporate relevant information from exogenous variables alongside endogenous variables. This joint consideration enables more accurate predictions and enhances the model’s overall performance. The proposed solution was thoroughly evaluated through realistic scenarios in a real factory environment with 5G connectivity and compared against main representatives of deep learning architectures (LSTM), machine learning techniques (Random Forest), and statistical methods (ARIMA) for time-series forecasting. We demonstrate that the deviation of AGVs can be effectively detected by using ensembles of our extended N-BEATS architecture that clearly outperform the other methods. Finally, a careful analysis of a real-time deployment of our solution was conducted, including retraining scenarios that could be triggered by the appearance of data drift problems.

Abstract In order to maintain adequate levels of cleanliness and sanitation in public facilities, prevent the buildup of viruses and other harmful pathogens, and ensure health and safety, health and labor authorities have repeatedly warned of the need to adhere to proper disinfection protocols in the workplace. This is particularly important in public places where food is handled, where there are more vulnerable people, including hospitals and health care centers, or where there is a large concentration of people. One promising approach is the combination of ultraviolet‐C (UV‐C) light and mobile robots to automate disinfection processes. Being this technology effective for disinfection, an excessive dose of UV can damage the materials, limiting its applicability. Therefore, a major challenge for automatic disinfection is to find a route that covers the entire surface, ensures cleanliness, and provides the correct radiation dose while preventing environmental materials from being damaged. To achieve this, in this paper a novel intelligent control approach is proposed. A bio‐inspired Glasius neural network with a motion planner, an UV estimation module, a speed regulator, and pure pursuit controller are combined into one intelligent system. The motion planner proposes a sequence of movements to go through the space in the most efficient way possible, avoiding obstacles of the environment. The speed controller adjusts the dose of UV‐C radiation and the pure pursuit regulator ensures the following of the path. This approach has been tested in various simulation scenarios of increasing complexity and in four different areas of dosing requirements. In simulation, a 44% reduction of the maximum dose is achieved, 17% less distance travelled by the robot and, what is more important, 229% more locations with the appropriate dose.

Wind turbine (WT) pitch control is a challenging issue due to the non-linearities of the wind device and its complex dynamics, the coupling of the variables and the uncertainty of the environment. Reinforcement learning (RL) based control arises as a promising technique to address these problems. However, its applicability is still limited due to the slowness of the learning process. To help alleviate this drawback, in this work we present a hybrid RL-based control that combines a RL-based controller with a proportional–integral–derivative (PID) regulator, and a learning observer. The PID is beneficial during the first training episodes as the RL based control does not have any experience to learn from. The learning observer oversees the learning process by adjusting the exploration rate and the exploration window in order to reduce the oscillations during the training and improve convergence. Simulation experiments on a small real WT show how the learning significantly improves with this control architecture, speeding up the learning convergence up to 37%, and increasing the efficiency of the intelligent control strategy. The best hybrid controller reduces the error of the output power by around 41% regarding a PID regulator. Moreover, the proposed intelligent hybrid control configuration has proved more efficient than a fuzzy controller and a neuro-control strategy.

Abstract This work focuses on the control of the pitch angle of wind turbines. This is not an easy task due to the nonlinearity, the complex dynamics, and the coupling between the variables of these renewable energy systems. This control is even harder for floating offshore wind turbines, as they are subjected to extreme weather conditions and the disturbances of the waves. To solve it, we propose a hybrid system that combines fuzzy logic and deep learning. Deep learning techniques are used to estimate the current wind and to forecast the future wind. Estimation and forecasting are combined to obtain the effective wind which feeds the fuzzy controller. Simulation results show how including the effective wind improves the performance of the intelligent controller for different disturbances. For low and medium wind speeds, an improvement of 21% is obtained respect to the PID controller, and 7% respect to the standard fuzzy controller. In addition, an intensive analysis has been carried out on the influence of the deep learning configuration parameters in the training of the hybrid control system. It is shown how increasing the number of hidden units improves the training. However, increasing the number of cells while keeping the total number of hidden units decelerates the training.