Digital twins enable real-time modeling, simulation, and monitoring of complex systems, driving advancements in automation, robotics, and industrial applications. This study presents a large-scale digital twin-testing facility for evaluating mobile robots and pilot robotic systems in a research laboratory environment. The platform integrates high-fidelity physical and environmental models, providing a controlled yet dynamic setting for analyzing robotic behavior. A key feature of the system is its comprehensive data collection framework, capturing critical parameters such as position, orientation, and velocity, which can be leveraged for machine learning, performance optimization, and decision-making. The facility also supports the simulation of discrete operational systems, using predictive modeling to bridge informational gaps when real-time data updates are unavailable. The digital twin was validated through a matrix manufacturing system simulation, with an Augmented Reality (AR) interface on the HoloLens 2 to overlay digital information onto mobile platform controllers, enhancing situational awareness. The main contributions include a digital twin framework for deploying data-driven robotic systems and three key AR/VR integration optimization methods. Demonstrated in a laboratory setting, the system is a versatile tool for research and industrial applications, fostering insights into robotic automation and digital twin scalability while reducing costs and risks associated with real-world testing.

Spatial Computing (SC) is an emerging paradigm that interlaces virtual 3D environments with physical ones, promising advancements in communication, teleoperation, education, and training. Despite its potential, accessibility of SC experiences across platforms is still a challenge. Virtual environments can be experienced using a diverse array of hardware interfaces, from conventional screens and keyboards to immersive head-mounted displays (HMDs) and full-body tracking suits, and these varying input modalities necessitate extra development efforts to maintain seamless user interaction across different devices and platforms. This paper introduces a concept of "Presence Drivers" (PDs), which offers a unified user representation for SC applications, independent of specific input devices. PDs function as a direct connection layer between the user's body and the SC application, simplifying the development of adaptive, user-friendly spatial software. The article discusses the PD concept within the current technological landscape, outlines its architecture, and proposes a reference implementation using Unity engine.

The integration of advanced extended reality technologies in the manufacturing and industrial context through the evolution of Industry 4.0 to the more user-centric Industry 5.0 paradigm guides the transformation of how end users access and control cyber-physical systems and real-time data sources. This is applicable both in real-world manufacturing contexts and higher education institutions, where future engineers learn how to design and manage these production systems. Extended reality (XR) has become an integral part of several aspects of industrial human-machine interaction methods, including diagnostic data visualization, teleoperation, augmented servicing and assembly instruction procedures, and safe operation of heavier machinery. In the educational context, XR allows for hands-on virtual activities, repeatability, and extended accessibility of limited resources before laboratory practical tasks. Since the pandemic, the digitalization of practical educational activities has been a central focus of pedagogical practices, leading to the development of specific engineering workflows. These integrate software and hardware solutions aimed at the implementation of XR experiences that fulfil the intended learning outcomes of the engineering product, process, and system design. In this paper, we present the design of an educational workflow for integrating manufacturing systems in XR-based learning environments. Two use cases are presented to demonstrate the relevance of the proposed workflow. The first provides an interactive experience that transfers laboratory teaching practices for pneumatics systems into an augmented reality (AR) application. The second focuses on the visualization and learning of direct kinematics methods for an industrial robotic arm.

Recent advancements in the field of digital manufacturing, especially the adoption of fast connectivity through 5G, Digital Twins and Extended Reality (XR) in manufacturing, offer new possibilities for innovative and effective design of production workflows. Augmented Reality (AR) can assist in speeding up the assembly and maintenance processes by facilitating the operators to perform these processes without dealing with detailed paper manuals. AR-based interactive user interfaces can support operators to be more productive by visualizing certain product and component 3D models dynamically, in addition to assembly steps along the corresponding manufacturing process. Likewise, AR-based applications can facilitate the setup and maintenance service of a machine by providing advanced machine visualization and digitalized information. This paper presents a conceptual model and case-based demo applications adopting AR technology for the maintenance of an industrial machine and supporting operators during the assembly process of a specific product. The goal is to improve productivity by reducing the processing time and minimize the operator training time. Moreover, the proposed AR application is integrated with the non-conformance reporting feature which helps to address the quality related issues quickly and efficiently, leading to a reduction in the number of nonconformities. Two case studies demonstrate the relevance of the proposed conceptual model and testing of the applications. (c) 2024 The Authors. Published by Elsevier B.V.

Modern manufacturing faces vastly changing challenges. The current economic situation and technological developments in terms of Industry 4.0 (I4.0) and Industry 5.0 (I5.0) force enterprises to integrate new technologies for more efficient and higher-quality products. Artificial intelligence (AI) and Machine Learning (ML) are the technologies that make machines capable of making human-like decisions. In the long run, AI and ML can add a layer (functionality) to make IoT devices more interactive and user-friendly. These technologies are driven by data and ML uses different types of data for making decisions. Our research focuses on testing a cobot-based quality control (CBQC) system that uses smart fixture and machine vision (MV) to determine the cables inside products with similar designs, but different functionality. The products are IoT modules for small electric vehicles used for interface, connectivity, and GPS monitoring. Previous research describes the methodology of reconfiguration of existing cobot cells for quality control purposes. In this paper, we discuss the testing of the CBQC system, together with creating a pattern database, training the ML model, and adding a predictive model to avoid defects in product cable sequence. Preliminary testing is carried out in the laboratory environment which leads to production testing in SME manufacturing. Results, developments, and future work will be presented at the end of the paper.

More than a decade ago, we were introduced to the concept of Industry 4.0 (I4.0), and today a lot has been applied in the manufacturing industry. Moreover, the concept of Industry 5.0 (I5.0) is spreading its branches, focusing on collaboration between humans and machines. The continuous development of collaborative robots (cobots) has led to a situation where Small and Medium-sized Enterprises (SMEs) have the financial resources, but lack of knowledge how to integrate these robot systems into their production by the principles of I4.0. The functions of the cobots meet the requirements of SMEs as these are easy to program, lightweight, and universal machines. In this article, we propose a methodology for reconstructing an existing cobot cell into an autonomous quality control system for SME production. This implies the use of Machine Vision (MV) technology with the development of various product databases, and in the future, adapting Machine Learning (ML) functionality. First, the variables are examined and classified by their features, determining their importance in the redesign process. Then, a digital twin model of the robotic system is developed to evaluate the effectiveness and simplify the preliminary programming of the system. This includes technology process-based design for elements such as gripper and multi-position fixture. Finally, we present the assembly and testing of the reconfigurable cobot-based quality control system with test results which imply that the quality control system can perform by the established goals.

The nature of the industry has undergone significant development over the past decade, moving towards digital production influenced by the concept of Industry 4.0. This development has been facilitated by the easy accessibility and relatively simple implementability of various technologies. Nearly all manufacturing processes are now robotized to increase and enhance productivity and quality. However, the process of robotization is complex, requiring consideration of various predetermined aspects, particularly concerning safety from a human perspective, where the process must be safe for humans. Nowadays, it is possible to employ simulation environments with digital avatars, providing a highly accurate digital replica of the real environment, taking into account various real-life physical dimensions. A major bottleneck in the design of the robotization process is achieving precise and realistic movement using inverse kinematics functionality. Analytical approaches are commonly used, necessitating the creation of specific mathematical formulas for each industrial robot model. They are applicable only when working with the given robot or similar industrial robots. This paper focuses on the CCD IK (Cycling Coordinate Descent Inverse Kinematics) implementation. This implementation aims to determine the correct angles of the robot's joints based on the end-effector's position in Cartesian space, also considering the end-effector's rotation.

Learning from Demonstration (LfD) is an approach to robot programming where the machine aims to replicate the task presented by a human without being explicitly programmed to execute this task. While being an effective way to create complex robot routines even for users without coding skills, most LfD implementations heavily rely on sensors for the robot to capture the state of the surrounding world and the task being demonstrated. In this research paper we offer an alternative LfD approach based on a fully simulated 3D environment. We demonstreate how simulation can eliminate the need for real-life sensors on the robot, serve as a unified medium for recording demonstrated tasks, and facilitate sharing of the produced solutions between different types of robotic cells with minimal to no reconfiguration. A Virtual Reality interface allows the operator to interact with the LfD environment in a natural way when recording task demonstrations for the robot. The system is built on top of commonly available software such as Unity engine, Robot Operating System, ROS-Industrial and MoveIt motion planning framework. It will be published on the public GitHub page of TalTech IVAR Lab [1]. We also provide a simple experimental procedure to validate the system’s ability to generate programs for multiple robot models from a single task demonstration, demonstrating its flexibility and ease of use for the operator.

Optimised human machine interfaces for multi-robot systems are essential for human in the loop in cyber-physical production lines and collaborative systems. The speed of changeover and customized production processes together with the need for straightforward easy and user-friendly human-machine interaction methods demands natural and adaptable interfaces. They should be based on flexible software cores and packages that ease and speed up the development processes. This also applies to laboratory testing and assessment in the academic field, in particular when it comes to the deployment of virtual or augmented reality (AR/VR) interfaces. The standardization of human-robot interaction including control methods in the extended reality domain is a work in progress. It needs broader assessment and clearer metrics to realise efficient and reliable tools. This work presents an Extended Reality (XR) user interface for the control and teleoperation of industrial robots. The systems allows the fast integration of the digital twins of robotic arms and path planning interface in AR and VR using Robot Operating System and Unity. Furthermore, a design-of-experiment involving two different robots (ABB IRB 1200 and ABB IRB 1600) in the two geographically distributed locations is proposed along with some preliminary experimental results.

Continuous change in manufacturing requires robotization, requiring a skilled workforce with robotic skills. It is also important for a manufacturing company to be able to transform its production process quickly. But now it is a long and complex process. The paper presents the simulation of the movement of an industrial robot in a digital environment, to which implemented the inverse kinematics functionality and machine learning model have been applied. The use of machine learning reduces the time required to develop the process and the investment in finding the path of the robot. The results obtained in the application of Bio-ik inverse kinematics and machine learning have been observed and analyzed as a simulation in the created research.

The high competition in the global market where the agile product launch and variable demand of goods by customers persuaded manufacturing companies to adopt Flexible Manufacturing System (FMS) and many companies have already implemented FMS solutions. On the other hand, manufacturing digitalization such as digital twin development, Industrial Virtual Reality (IVR), virtual modeling and 3D simulation of manufacturing systems offer new possibilities for effective facility layout planning, quick and easy modification and validation of production processes, analysis, and optimize the workflow and activities conducted on a factory floor. These new technological developments in digitalization have changed the thinking of manufacturing companies and they are eager to use digitalization solutions in their factory operations. However, there is a lack of harmonized methods and procedures to implement virtual modeling, 3D simulation, and IVR for layout planning and analysis of FMS. This paper proposed an approach for performance analysis of a FMS that is based on the 3D layout creation and simulation in a virtual environment, monitoring of key performance indicators via a digital dashboard, and immersive visualization through virtual reality. The relevance and feasibility of the proposed performance analysis approach are demonstrated by a case study.

The advent of Industry 4.0 is changing the role of human labour towards a more supportive function in the production system, requiring new digital-, technical-, interdisciplinary-, collaborative- and communicative competencies. This challenges educational institutions to develop new teaching activities and materials to address ever emerging needs. To address this, this paper presents an Educational Framework to support educators in developing new teaching activities and study material for Industry 4.0. The model distinguishes itself from other educational design models by combining an iterative approach toward problem-solving, with the concept of authentic task design, as the core elements. Based on 14 pilot cases, it is concluded that educational framework have increased the educational activities in the areas in focus.

Timber industry is one of the most relevant economic sectors in Estonia. Automatization of forestry management and harvesting processes optimization are realities also in this specific domain. As much as in other industrial fields adopting the Industry 4.0 paradigm and core technologies, forestry management, log harvesting and the wood processing industry make use of state-of-the-art sensors, Digital Twins and advanced interfaces for the operators. The latter include Extended Reality solutions and remote-control making use of immersive head mounted displays (HMD). This works presents an innovative system for hydraulic forestry crane teleoperation making use of HMD and wide-angle camera stream. The system hardware is installed locally while the software, integrated in Unity, supports the operator in using the crane’s native joysticks and controller for the log loading operations. Additional virtual user interface and controls are included in the immersive view and accessible through the same controls and joysticks.

Mild cognitive impairment (MCI) is an early stage of cognitive abilities loss and puts older adults at higher risk of developing dementia. Virtual reality (VR) could represent a tool for the early assessment of this pathological condition and for administering cognitive training. This work presents a study evaluating the acceptance and the user experience of an immersive VR application representing a supermarket. As the same application had already been assessed in Italy, we aimed to perform the same study in Estonia in order to compare the outcomes in the two populations. Fifteen older adults with MCI were enrolled in one Rehabilitation Center of Estonia and tried the supermarket once. Afterwards, they were administered questionnaires aimed at evaluating their technology acceptance, sense of presence, and cybersickness. Estonian participants reported low side effects and discrete enjoyment, and a sense of presence. Nonetheless, their intention to use the technology decreased after the experience. The comparison between Italian and Estonian older adults showed that cybersickness was comparable, but technology acceptance and sense of presence were significantly lower in the Estonian group. Thus, we argue that: (i) cultural and social backgrounds influence technology acceptance; (ii) technology acceptance was rather mediated by the absence of positive feelings rather than cybersickness.

Universal solutions for industrial robot integration are urgent requirements for companies looking for machine interconnectivity, and tailor-made manufacturing systems design. These solutions must be supported by modular and open-source components and Extended Reality (XR) interfaces. Robot Operating System (ROS) has proven to be a reliable, interoperable and modular standard for industrial robot integration. Digital Twins (DT) of industrial equipment and processes offer a solid base to develop innovative digital tools relying on synchronization between physical and digital entities and the setup of XR interfaces for teleoperation and programming. This work presents the integration of the OMRON TM5-9000 collaborative industrial robot into the IVAR laboratory DT system at Tallinn University of Technology. By using Unity3D game engine and developing a ROS package for the specific machine, the digital model of the collaborative robot is integrated into the existing twin, synchronized with the real counterpart, and controlled by a remote user interface.

The adoption of Digital Twin (DT) solutions for industrial purposes is increasing among small- and medium-sized enterprises and is already being integrated into many large-scale companies. As there is an increasing need for faster production and shortening of the learning curve for new emerging technologies, Virtual Reality (VR) interfaces for enterprise manufacturing DTs seem to be a good solution. Furthermore, with the emergence of Industry 5.0 (I5.0) paradigm, human operators will be increasingly integrated in the systems interfaces though advanced interactions, pervasive sensors, real time tracking and data acquisition. This scenario is especially relevant in collaborative automated systems where the introduction of immersive VR interfaces based on production cell DTs might provide a solution for the integration of the human factors in the modern industrial scenarios. This study presents experimental results of the comparison between users controlling a physical industrial robot system via a traditional teach pendant and a DT leveraging a VR user interface. The study group involves forty subjects including experts in robotics and VR as well as non-experts. An analysis of the data gathered in both the real and the virtual use case scenario is provided. The collected information includes time for performing a task with an industrial robot, stress level evaluation, physical and mental effort, and the human subjects’ perceptions of the physical and simulated robots. Additionally, operator gazes were tracked in the VR environment. In this study, VR interfaces in the DT representation are exploited to gather user centered metrics and validate efficiency and safety standards for modern collaborative industrial systems in I5.0. The goal is to evaluate how the operators perceive and respond to the virtual robot and user interface while interacting with them and detect if any degradation of user experience and task efficiency exists compared to the real robot interfaces. Results demonstrate that the use of DT VR interfaces is comparable to traditional tech pendants for the given task and might be a valuable substitute of physical interfaces. Despite improving the overall task performance and considering the higher stress levels detected while using the DT VR interface, further studies are necessary to provide a clearer validation of both interfaces and user impact assessment methods.

The continuous need to develop Industry 4.0 branches has led to a position, where highly sophisticated and multi-layer smart robotic systems are conducting the way in future manufacturing. This study aims to build a connectivity and system intelligent layer on top of a Co-bot integrated CNC-based Manufacturing cell. The connectivity layer is used to bypass all the data from machines to the upper intelligent layer vice versa. When raw data is arriving in the intelligent layer it is converted to information and again to knowledge for reflection back to the cell. Machine to Machine Communication and Digital Twin process for optimization is used for data conversions. This study is a down-scale example of the CPS for further development of existing robot cells.

The growing relevance of digitalization in production requires the enhancement of human skills and competences in the field of Information and Communication Technology (ICT). Higher education has to cope with this need by providing the necessary ICT skills to future industrial engineers, so that they have a good understanding of the complexity of industries in the 21st century. This paper presents the conceptual development and testing of a Virtual Learning Factory Toolkit (VLFT) that integrates digital tools used in production management with engineering education. The digital tools integrated into the VLFT can help students to exploit enabling technologies such as simulation and virtual reality in their manufacturing studies and practical projects with industrial companies. Moreover, digital tools were tested by using a structured workflow that consists of different learning activities related to manufacturing system configuration. Students practised the digital tools with the help of use cases in the form of joint learning labs, after which the students' feedback was collected and analysed.

The new paradigm of digital manufacturing and the concept of Industry 4.0 has led to the integration of recent manufacturing advances with modern information and communication technologies. Therefore, digital simulation tools fused into production systems can improve time and cost-effectiveness and enable faster, more flexible, and more efficient processes to produce higher-quality goods. The advancement of digital simulation with sensory data may support the credibility of production systems and improve the efficiency of production planning and execution processes. In this paper, an approach is proposed to develop a Digital Twin of production systems in order to optimize the planning and commissioning process. The proposed virtual cell interacts with the physical system with the help of different Digital Manufacturing Tools (DMT), which allows for the testing of various programs in a different scenario to check for any shortcomings before it is implemented on the physical system. Case studies from the different production systems are demonstrated to realize the feasibility of the proposed approach.

Industrial Digital Twins (DT) is the precise virtual representation of the manufacturing environment and mainly consists of the system-level simulation, which combines both manufacturing processes and parametric models of the product. As being one of the pillars of the Industry 4.0 paradigm, DT-s are widely integrated into the existing factories, enhancing the concept of the virtual factories. View from the research perspective is that experiments on the Internet of Things, data acquisition, cybersecurity, telemetry synchronization with physical factories, etc. are being executed in those virtual simulations. Moreover, new ways of interactions and interface to oversee, interact and learn are being developed via the assistance of Virtual Reality (VR) and Augmented Reality (AR) technologies, which are already widely spread on the consumer market. However, already, VR is being used widely in existing commercial software packages and toolboxes to provide students, teachers, operators, engineers, production managers, and researchers with an immersive way of interacting with the factory while the manufacturing simulation is running. This gives a better understanding and more in-depth knowledge of the actual manufacturing processes, not being directly accessing those. However, the virtual presence mentioned above experience is limited to a single person. It does not enable additional functionalities for the simulations, which can be re-planning or even re-programming of the physical factory in an online connection by using VR or AR interfaces. The main aim of the related research paper is to enhance already existing fully synchronized with physical world DT-s with multi-user experience, enabling factory operators to work with and re-program the real machinery from remote locations in a more intuitive way instead thinking about final aim than about the process itself. Moreover, being developed using real-time platform Unity3D, this multiplayer solution gives opportunities for training and educational purposes and is connecting people from remote locations of the world. Use-cases exploits industrial robots placed in the Industrial Virtual and Augmented Reality Laboratory environment of Tallinn University of Technology and a mobile robot solution developed based on a collaboration between the University of Southern Denmark and a Danish company. Experiments are being performed on the connection between Estonia and Denmark while performing reprogramming tasks of the physical heavy industrial robots. Furthermore, the mobile robot solution is demonstrated in a virtual warehouse environment. Developed methods and environments together with the collected data will enable us to widen the use-cases with non-manufacturing scenarios, i.e., smart city and smart healthcare domains, for the creation of a set of new interfaces and multiplayer experiences.