In recent advancements in robotics, Artificial Intelligence (AI) methods such as Deep Learning, Deep Reinforcement Learning (DRL), Transformers, and Large Language Models (LLMs) have significantly enhanced robotic capabilities. Key AI models driving advancements in robotic vision include Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), the DEtection Transformers (DETR), the YOLO family of algorithms, segmentation techniques, and 3D vision technologies. Deep Reinforcement Learning (DRL), an AI technique where agents learn optimal behaviors through trial and error interactions with their environment, enables robots to perform complex tasks autonomously. Transformers, originally developed for natural language processing, have been adapted to robotics for tasks involving sequence prediction and data understanding, improving perception and decision-making processes. LLMs leverage vast amounts of text data to enhance robot-human interaction, enabling robots to understand and generate human-like language, thus improving their communicative and collaborative abilities in various applications. The integration of these AI methods enhances the adaptability, efficiency, and overall performance of robotic systems, paving the way for more sophisticated and intelligent autonomous agents.

In the era of Industry 4.0, service robot path planning has emerged as a pivotal element in the optimization of logistic tasks within manufacturing, warehousing and service applications. In this context, the adoption of advanced path planning algorithms, such as the Grey Wolf Optimizer (GWO) swarm algorithm, play a key role in enabling these robots to navigate through complex environments with precision and agility. Harnessing the power of bio-inspired algorithms, our framework establishes a methodical and effective approach to the intricate task of service robot path planning.

This paper highlights the growing importance of edge computing and the need for AI techniques to enable intelligent processing at the edge. Edge computing has emerged as a paradigm shift that brings data processing and storage closer to the source, minimizing the need for transmitting large volumes of data to remote locations. The integration of AI capabilities at the edge enables intelligent and real-time decisionmaking on resource-constrained devices. This paper discusses the significance of Edge AI across various domains, including automotive applications, smart homes, industrial IoT, and healthcare. By leveraging AI algorithms on edge devices, efficient implementation and deployment become possible, leading to improved latency, privacy, and security.The various AI techniques used in edge computing are presented, including machine learning, deep learning, reinforcement learning and transfer learning. As AI continues to play a pivotal role in driving edge computing, the integration of hardware accelerators and software platforms is gaining utmost significance to efficiently run inference models. A variety of popular options have emerged to accelerate AI at the edge, and notable among them are NVIDIA Jetson, Intel Movidius Myriad X, and Google Coral Edge TPU. The importance of specialized System-on-a-Chip (SoC) solutions for Edge AI, capable of supporting high-performance video, voice, and vision processing alongside integrated AI accelerators is presented as well. By examining the transformative potential of Edge AI, this paper aims to inspire researchers, practitioners, and industry professionals to explore the vast possibilities of integrating AI at the edge. With Edge AI reshaping the future of edge computing, intelligent decision-making becomes seamlessly integrated into our daily lives, driving advancements across various sectors.

Currently, the world is facing major changes. Research and development of innovations in new technologies, the rapid pace of implementation of these innovations and especially digitization and automation, play a major role in shaping the future world. Technological innovations promise the transformation of the world we live in all its dimensions. However, in order for the benefits of innovation to be adequately exploited, it is necessary for us as a society to adapt to the coming changes. We must also keep in mind that these changes come at a time previously marked by uncertainty, turbulent changes and hyper competitiveness. The development and implementation of new technologies in business is motivated by a number of technical and economic reasons: improving the quality of finished products (machining, etc.), increasing productivity and reducing the share of work (assembly process), increasing the degree of homogeneity of product quality in all production processes related to the application of robotic technology, increasing the level of safety, reducing labor engagement in routine and reproducible processes, minimizing total production costs and maintenance costs of the device in the production process, all with the purpose of adequate responses to competition challenges and increasingly stringent customer requirements. Although the concept of Industry 4.0 is already widely used in developed countries, it is a relatively new concept in the Western Balkans, including Bosnia and Herzegovina. Most company managers understand the benefits of "smart" production and are familiar with new trends in the industry, intend to gradually introduce smart solutions, methods and technologies, and only a small number of companies in Bosnia and Herzegovina currently implement the concept of Industry 4.0. The paper presents the results of research on the application of Industry 4.0 technologies in all branches of the economy in Bosnia and Herzegovina and especially the representation of Industry 4.0 in small, medium and large enterprises. Detection of awareness of certain groups about the concepts of Industry 4.0 was performed, and the research method itself is based on an online survey.

Artificial intelligence (AI) is a very disruptive technology, which combined with powerful computational hardware have opened new possibilities for world-wide technological progress in industry. There is an urgent need for systematic development and implementation of AI to see its real impact in the next generation of industrial systems, namely Industry 4.0. Organisations that do not do so will fail to maintain their competitiveness. This paper provides an insight into the main paradigms of AI technologies used in Industry 4.0, by giving emphasis to the key enabling digitalization technologies and their challenges. In addition, we present an overview of AI current state and the most important AI algorithms used in Industry 4.0. Finally, we discuss trends related to adoption of AI in the context of software embedded applications and software architectures for embedded systems.

Vještačka inteligencija (VI) je veoma disruptivna tehnologija, koja u kombinaciji sa snažnim hardverom za procesiranje otvara mogućnosti za opšti napredak u industriji. Postoji hitna potreba za sistemskim razvojem i implementacijom VI radi njenog učinka u industrijskim sistemima, posebno u četvrtoj industrijskoj revoluciji (Industrija 4.0). Tržišni subjekti koji ne usvoje VI neće biti u mogućnostiodržati svoju konkurentnost na tržištu. Ova publikacija pruža uvid u glavne paradigme VI korištene u Industriji 4.0, stavljajući naglasak na ključne digitalne tehnologije i njihove izazove. Pored toga, u ovoj publikaciji smo napravili pregled trenutnog stanja u VI, te pregled najvažnijih algoritama korištenih u Industriji 4.0. Pored navedenih tema, u ovoj publikaciji diskutujemo i o trendovima vezanim za usvajanje VI u kontekstu ugradbenih aplikacija i softverskih arhitektura uopšteno.

Due to COVID-19 pandemic, there is an increasing demand for mobile robots to substitute human in disinfection tasks. New generations of disinfection robots could be developed to navigate in high-risk, high-touch areas. Public spaces, such as airports, schools, malls, hospitals, workplaces and factories could benefit from robotic disinfection in terms of task accuracy, cost, and execution time. The aim of this work is to integrate and analyse the performance of Particle Swarm Optimization (PSO) algorithm, as global path planner, coupled with Dynamic Window Approach (DWA) for reactive collision avoidance using a ROS-based software prototyping tool. This paper introduces our solution – a SLAM (Simultaneous Localization and Mapping) and optimal path planning-based approach for performing autonomous indoor disinfection work. This ROS-based solution could be easily transferred to different hardware platforms to substitute human to conduct disinfection work in different real contaminated environments.

Improvements in energy efficiency in Industry 4.0 is the main imperative in manufacturing. An important challenge in many fields of complex industrial processes is energy-efficient optimization. The basic idea of the energy efficiency optimization algorithm is to find the optimal assigned value of process parameters to achieve the lowest energy cost and the best working conditions. Applying the multi-objective approach for solving real industry optimization problems is a challenging task. Therefore, this chapter provides an overview of the most significant issues in multi-objective optimization problem. Improving energy efficiency with the multi-objective optimization has opened new opportunities for technological progress in Industry 4.0.

Intelligent manufacturing plays an important role in Industry 4.0. Key technologies such as artificial intelligence (AI), big data analytics (BDA), the internet of things (IoT), cyber-physical systems (CPSs), and cloud computing enable intelligent manufacturing systems (IMS). Artificial intelligence (AI) plays an essential role in IMS by providing typical features such as learning, reasoning, acting, modeling, intelligent interconnecting, and intelligent decision making. Artificial intelligence's impact on manufacturing is involved in Industry 4.0 through big data analytics, predictive maintenance, data-driven system modeling, control and optimization, human-robot collaboration, and smart machine communication. The recent advances in machine and deep learning algorithms combined with powerful computational hardware have opened new possibilities for technological progress in manufacturing, which led to improving and optimizing any business model.

For unstructured environments, multi-leg platforms such as hexapods, introduce better stability and adaptation during the moving in a more complex environment. The common hexapod robots, which are controlled by discrete conventional microcontrollers would require new chip replacement due to I/O constraint. With an FPGA, the user can scale design and include new functionality later in the design process without buying new additional hardware. In this paper, we introduce the hybrid architecture as a combination of FPGA and microcontroller design. The goal of this work is to extend context arbitration of a fuzzy behavior-based approach for hexapod robot navigation at the FPGA device. Verilog has been used to develop FLC on FPGA. The controller algorithm is developed and implemented on FPGA Altera Cyclone IV board. An experimental evaluation of hexapod autonomous navigation at a rough terrain presents advantages of this hierarchy approach for real-time robot embedded systems.