This paper presents the development and experimental validation of an adaptive pneumatic gripper for collaborative robotic palletizing of packages with varying mass and surface characteristics. The main objective is to determine the optimal gripping-force and minimum operating pressure required to ensure stable and safe handling without slippage. A dynamic mathematical model was developed, incorporating the effects of package mass, friction coefficient, contact surface area, and inertial forces during manipulation. Numerical analysis was performed for different friction conditions (μ = 0.30-0.90) and contact configurations, enabling the determination of the minimum required gripping-forces and corresponding operating pressures. Experimental validation was conducted on a real industrial system with a collaborative robot. The results show a linear relationship between pressure and gripping-force, described by F = 22.152 p − 17.535, with a high correlation coefficient (R2 ≈ 0.998). The maximum experimentally obtained gripping-force was approximately 70-75 N at a pressure of around 4 bar. Quantitative deviations between numerical and experimental results (65-75 %) were observed and corrected by introducing a calibration factor (kcorr ≈ 0.30). The proposed model and experimental system enable reliable optimization of gripping-force and improve manipulation stability under real industrial conditions. The main contribution of this study lies in the integration of analytical modelling, numerical optimization, and industrial experimental validation for collaborative robotic palletizing systems

The integration of technology in correctional facilities represents a paradigm shift in modern prison rehabilitation approaches globally, offering unprecedented opportunities to enhance inmate reintegration while addressing systemic challenges. This research examines the global phenomenon of digital rehabilitation, using the current state and prospects of technology adoption in Albanian prisons as an illustrative case study. By analysing both opportunities for rehabilitation enhancement and implementation challenges, this study highlights the broader implications of digital tools in correctional settings. Through a comprehensive analysis of recent developments from 2020 to 2025, including international cooperation initiatives, this study reveals significant potential for digital transformation in correctional systems. Key findings indicate that technology-enhanced rehabilitation programs can reduce recidivism rates by up to 23% compared to traditional methods, while digital education platforms show 68% success rates versus 35% for conventional approaches. However, implementation faces substantial barriers globally, including high costs (85% impact), ageing infrastructure (78% impact), and staff training requirements (72% impact). The research demonstrates that strategic   technology adoption, supported by international partnerships and phased implementation approaches, can transform prisons into modern rehabilitation-focused institutions. This study contributes to the growing body of international knowledge on correctional technology, providing insights that are transferable to other transitional contexts and informing global policy decisions.

The first industrial robots appeared in the production processes in the 1960s have continued to be implemented in manufacturing worldwide. The greatest application of industrial robots has been observed in three major industries: the automotive industry, the electrical and electronics industry, and the metal industry. The automotive industry was the first to adopt the most industrial robots extensively, and in recent years the electrical and electronics industry has followed. Together, these two sectors account for more than 60% of the total number of industrial robots deployed worldwide. Industrial robots have primarily been used to perform tasks that are physically demanding and hazardous to workers’ health, including welding operations, which are predominantly carried out in the automotive industry. To date, first-generation industrial robots have been the most widely implemented. These systems are typically enclosed by protective fences to ensure worker safety, occupy substantial floor space, and are relatively complex to reprogram. The development of advanced technologies — such as sensor systems, the Internet of Things (IoT), big data analytics, cloud computing, virtual and augmented reality (AR), artificial intelligence (AI), and advanced safety systems — has significantly contributed to the evolution of robotic technology. The present study presents current trends in the implementation of industrial robots and examines their role in welding processes.

This paper investigates the potential of Explainable Artificial Intelligence (XAI) methods to improve the interpretation of AI-based models in smart manufacturing applications. The study focuses on SHAP and LIME techniques, analyzing their ability to explain model decisions, identify the most influential input features, and provide insights into both individual predictions and overall model behaviour. A practical case study based on the Steel Plates Faults dataset is presented using a Random Forest classification model to investigate the application of explainable AI techniques for steel plate fault detection. The results demonstrate that SHAP and LIME methods provide valuable insights into model decision-making by identifying the key features influencing fault classification. These explainability approaches enhance model transparency and trustworthiness, supporting the development of more reliable AI-based solutions for industrial quality inspection and smart manufacturing applications.

Research and development of advanced technologies underpinning the implementation of Industry 4.0 are driving the transformation of traditional manufacturing systems into flexible production systems whose high level of integration and intelligence is based on digital technologies. Mobile and collaborative robotics, supported by artificial intelligence, are becoming central elements of intelligent manufacturing processes through their implementation, complementing other Industry 4.0 technologies. This paper provides a clear and comprehensive overview of the architecture of Industry 4.0 smart manufacturing systems based on the integration of autonomous mobile robots and collaborative robots, with particular emphasis on system hierarchy, data flows, and interoperability with existing industrial information systems. Patent trends over the past decade in robotics and artificial intelligence are analyzed, along with trends in the implementation of mobile and collaborative robots in manufacturing processes. The role of robotic systems in process monitoring, decision-support, and adaptive production control is examined, including their integration with IoT platforms, manufacturing execution systems, and AI-based analytical modules. The paper also discusses the technical and organizational challenges associated with implementing such architectures, as well as their potential benefits in terms of flexibility, scalability, and resilience of manufacturing systems. The proposed architectural approach provides a foundation for the further development of smart manufacturing environments and offers guidelines for the industrial application of mobile and collaborative robotics in accordance with Industry 4.0 principles.

One of the characteristics of today's world economic trends is market expansion, i. e. the need for constant modification of existing products through application of new technologies, which should ensure competitiveness in turbulent market conditions. The role of industrial and service robots is essential in such conditions of manufacturing processes. An industrial and service robot is an essential constituent element of the new manufacturing lines, which are designed on a high degree of automation with the characteristics of flexibility, where it is very difficult to observe the robot and its effect outside the whole manufacturing line. The inclusion of industrial and service robots in existing production facilities increases significantly the performance of existing equipment, ensuring its efficiency. This reduces or postpones the need for new or larger investments, since certain situations have shown that the acquisition of robots is much more economical than purchasing new machines. The application of robotic systems in manufacturing processes, whether it is a fully automated process or highly automated manufacturing line (the so-called fixed automation or a possible flexible manufacturing cell), is observed through: materials handling and supporting machines, process operations, assembly tasks, and tasks of products inspection. The paper describes the dissemination of industrial and service robots in the world in the period 2009 to 2014, through the application in specific operations in the manufacturing process.

Industry 4.0 marks a new phase of industrial transformation, driven by the integration of advanced technologies such as industrial robotics, the Internet of Things (IoT), artificial intelligence (AI), cloud computing, and cyber‑physical systems (CPS). The Republic of Korea and Singapore are global frontrunners in this domain, ranking first and second worldwide in robot density per 10,000 manufacturing workers. This paper explores how the strategic integration of robotics with key Industry 4.0 technologies contributes to smart manufacturing and enhanced industrial performance. Using a comparative case study approach, the research analyzes national policies, investments in R&D and education, 5G infrastructure, and support for innovation ecosystems that have enabled these countries to develop flexible, automated, and intelligent production systems. Findings indicate that both Korea and Singapore have successfully combined robotics with IoT, big data analytics, and cloud platforms to create efficient and adaptive manufacturing environments. The study emphasizes that robotization alone is not sufficient; its effectiveness depends on alignment with broader digital transformation strategies. Based on longitudinal data from 2013 to 2023, sourced from the International Federation of Robotics (IFR), the OECD, and national innovation agencies, the research highlights how coordinated implementation of Industry 4.0 technologies fosters sustainable and globally competitive manufacturing.

The integration of human-robot collaboration (HRC) into industrial and service environments demands efficient and adaptive robotic systems capable of executing diverse tasks, including pick-and-place operations. This paper investigates the application of Soft Actor-Critic (SAC) and Conservative Q-Learning (CQL)—two deep reinforcement learning (DRL) algorithms—for the learning and optimization of pick-and-place actions within HRC scenarios. By leveraging SAC’s capability to balance exploration and exploitation, the robot autonomously learns to perform pick-and-place tasks while adapting to dynamic environments and human interactions. Moreover, the integration of CQL ensures more stable learning by mitigating Q-value overestimation, which proves particularly advantageous in offline and suboptimal data scenarios. The combined use of CQL and SAC enhances policy robustness, facilitating safer and more efficient decision-making in continually evolving environments. The proposed framework combines simulation-based training with transfer learning techniques, enabling seamless deployment in real-world environments. The critical challenge of trajectory completion is addressed through a meticulously designed reward function that promotes efficiency, precision, and safety. Experimental validation demonstrates a 100 % success rate in simulation and an 80 % success rate on real hardware, confirming the practical viability of the proposed model. This work underscores the pivotal role of DRL in enhancing the functionality of collaborative robotic systems, illustrating its applicability across a range of industrial environments.