Intelligent Robotics

When interacting with each other, humans adjust their behavior based on perceived trust. To achieve similar adaptability, robots must accurately estimate human trust at sufficiently granular timescales while collaborating with humans. Beta reputation is a popular way to formalize a mathematical estimation of human trust. However, it relies on binary performance, which updates trust estimations only after each task concludes. Additionally, manually crafting a reward function is the usual method of building a performance indicator, which is labor-intensive and time-consuming. These limitations prevent efficient capture of continuous trust changes at more granular timescales throughout the collaboration task. Therefore, this letter presents a new framework for the estimation of human trust using beta reputation at fine-grained timescales. To achieve granularity in beta reputation, we utilize continuous reward values to update trust estimates at each timestep of a task. We construct a continuous reward function using maximum entropy optimization to eliminate the need for the laborious specification of a performance indicator. The proposed framework improves trust estimations by increasing accuracy, eliminating the need to manually craft a reward function, and advancing toward the development of more intelligent robots.

In the context of Industry 4.0, cloud computing offers the scalability, flexibility, and wide range of services required to facilitate big data analytics. This enables enterprises to extract meaningful insights from the vast amounts of data produced by intelligent and networked production processes. Industry 4.0 demands real-time decision-making as cloud-based analytics enable quick processing of streaming data for immediate insights. The combination of big data analytics and cloud computing is driving the digital age in order to expand the processing power. Organizations can expand their computer capabilities according to the amount of data and processing demands thanks to cloud platforms. Cloud computing increases productivity and enables predictive maintenance by analyzing equipment data in real-time and reducing downtime. By evaluating data from several sources, cloud-based analytics enhance supply chain operations and facilitate better inventory control and logistics. Furthermore, real-time processing at the point of data production is made possible by the developing combination of edge computing and cloud analytics, which lowers latency. The present assessment underscores the revolutionary effect of merging big data analytics and cloud computing within the framework of Industry 4.0, stressing the benefits, obstacles, applications, and forthcoming patterns in this everevolving domain. The goal of this in-depth analysis is to further our knowledge of how important it will be for Industry 4.0 to integrate Big Data analytics with cloud computing.

El diseño manual de funciones de recompensa para el Aprendizaje por Refuerzo (RL) en robótica es complejo y propenso a errores. Este trabajo investiga la automatización de dicho proceso mediante Grandes Modelos de Lenguaje (LLMs), ampliando la metodología Eureka. Se evaluó la capacidad de diversos LLMs del mercado, más allá de GPT-4 y GPT-3.5 estudiados en el trabajo original, para generar recompensas en tres tareas de manipulación robótica con las manos Shadow y Allegro en el simulador Isaac Gym. Los resultados muestran que los LLMs, especialmente modelos recientes y aquellos con razonamiento Chain-of-Thought, pueden superar las recompensas diseñadas por expertos humanos en el 100 % de las tareas evaluadas, logrando éxito en entornos de alta complejidad como pen spinning con la Allegro Hand. Modelos como O1 y algunas variantes de Claude destacan significativamente. El estudio confirma el gran potencial de los LLMs para optimizar el diseño de recompensas en RL aplicado a la realización de tareas complejas en robótica.

With the support of intelligent machinery systems and control software, the manufacturing industry has rapidly transformed. The application of technology is making production processes increasingly smart and delivering significant benefits. Businesses can adopt smart manufacturing to modernize operations, enhance productivity, maintain competitiveness, and prepare for future challenges. Therefore, developing a workforce capable of working within smart manufacturing systems is an urgent task. It is essential to have human resources equipped with the knowledge and skills to design, install, operate, troubleshoot, and maintain intelligent machinery and systems. This paper provides reliable research data and comprehensive information about smart manufacturing and its ecosystem. It also proposes several solutions to improve the quality of training in higher education institutions. Based on these findings, educational institutions specializing in technological and engineering fields can make appropriate and flexible decisions when implementing training programs aligned with smart manufacturing systems. This ensures optimal teaching effectiveness and produces a skilled workforce that meets the demands of flexible manufacturing enterprises in the era of advanced technology.

This research explores the transformative role of Internet of Things (IoT)-based predictive maintenance in promoting energy efficiency and operational excellence within the manufacturing sector. With rising operational demands and environmental responsibilities, industries are shifting from reactive and time-based maintenance to proactive, data-driven systems. This study presents a fictional case rooted in realistic industrial practices to demonstrate how predictive maintenance reduces energy usage, operational downtime, and long-term costs. The findings indicate that when supported by IoT infrastructure, predictive maintenance serves as a key enabler of sustainable manufacturing practices, strategic agility, and industrial resilience in the age of digital transformation.

The application of Artificial Intelligence (AI) in mechanical engineering operations is transforming traditional processes, enhancing efficiency, and enabling optimization across various domains such as design, manufacturing, maintenance, and quality control. This study explores the integration of AI technologies like machine learning, deep learning, robotics, and data analytics in mechanical engineering, with a focus on their roles in process optimization. By leveraging AI, engineers can predict equipment failures, reduce downtime, optimize designs, and improve overall productivity. Despite the significant advantages, the implementation of AI also faces challenges, including technical barriers and resistance to change. The study also discusses future opportunities for AI in mechanical engineering, including advancements in reinforcement learning, quantum computing, and edge AI. As AI continues to evolve, it holds the potential to redefine the future of mechanical engineering by fostering innovation, sustainability, and greater operational efficiency.

In the framework of Smart Manufacturing, a crucial element of Industry 4.0, the incorporation of Artificial Intelligence (AI) in human-robot cooperation (HRC) has become a revolutionary influence. With an emphasis on how intelligent systems are enhancing productivity, flexibility, and safety in industrial settings, this paper examines the developments and difficulties of AI-enhanced HRC. By enhancing collaboration between humans and robots, AI ensures faster and more efficient production processes. AI-powered robots can assess the environment and reduce risks to human workers by taking over dangerous or strenuous tasks. By leveraging machine learning, computer vision, and real-time data analytics, AI enables robots to perform complex tasks alongside human workers with improved decision-making, adaptability, and situational awareness. AI enables robots to perform a variety of tasks, adapting quickly to new manufacturing setups, which is essential in custom or smallbatch production. Predictive maintenance and AI-driven quality control help to reduce downtime and waste, leading to lower operational costs. The review highlights AI's role in optimizing task allocation, enhancing communication between humans and robots, and fostering a dynamic, collaborative workspace. Key case studies in automotive, electronics, and aerospace sectors demonstrate significant improvements in operational efficiency and quality control through AI-empowered robotic systems. However, ethical considerations, human-centered design, and addressing workforce skills gaps remain critical for the widespread adoption of AI in collaborative robotics. This paper provides a comprehensive overview of current trends, future directions, and the potential of AI-enhanced HRC to revolutionize smart manufacturing.

A multi-point navigation method is introduced for intelligent inspection robots, aimed at enhancing efficiency and safety across various industries. The newly proposed WW algorithm improves the robots' fault tolerance and positioning accuracy. The study utilized tools such as the ROS operating system, Rviz, and Gazebo, as well as the Agilex Bunker MINI intelligent trolley and SCOUT MINI sensor platform. It discussed SLAM map construction with Cartographer and Gmapping algorithms and the AMCL positioning system. Additionally, the DWA algorithm for dynamic obstacle avoidance was introduced. The system design includes a Qt interface and Rviz interface for multi-point navigation and obstacle avoidance. The effectiveness of the WW algorithm was verified through simulations and experiments, which enhances navigation stability by setting a maximum standby time and alternative point strategy. The experimental results show that the WW algorithm can prevent the robot from entering a false dead state. The paper concludes with suggestions for further optimization of the algorithm and the integration of more complex intelligent functions using deep learning.

To effectively develop and implement a comprehensive data governance and cybersecurity framework, it's essential to have a clear understanding of the current state of data management and cybersecurity practices within the Architect of the Capitol (AOC).

Control theory has been a cornerstone in the development of modern industrial systems, enabling automation, optimization, and reliability across various sectors worldwide. This paper explores the latest advancements in the application of control theory in industrial settings, focusing on innovative methodologies, practical implementations, and emerging challenges. We present case studies from manufacturing, energy, and robotics industries, highlighting how control theory has been leveraged to improve efficiency, reduce costs, and enhance system performance. Additionally, we discuss the integration of advanced control strategies, such as model predictive control (MPC), adaptive control, and machine learningbased control, in addressing complex industrial problems. The paper concludes with a forward-looking perspective on the future of control theory in industry, emphasizing the role of digital transformation, cyber-physical systems, and sustainable practices.

A robotic gym equipped with several rehabilitation robots enables multiple patients to engage in simultaneous exercise, all overseen by one therapist. The effectiveness of multipatient training could potentially be enhanced by dynamically allocating patients to specific robots based on continuously monitored patient data. This paper focuses on training an Inverse Reinforcement Learning agent for dynamic patient-robot task assignment in a multi-patient, multirobot rehabilitation gym. The agent learns a reward model that comprehensively captures the intricacies of the expert's assignment strategy based on expert data, exhibiting improved generalization capabilities for unseen scenarios compared to our previous work using supervised learning. The output of the reward model estimates if the assignment follows the domain expert's underlying assignment strategy. The proposed approach was evaluated using a simulator designed to emulate the outcomes of patient exercises with robots. Our proposed method achieved similar performance to that of a domain expert and outperformed four baseline assignment methods.

The undersigned hereby certify that they have read and recommend to the Faculty of Mechanical, Maritime and Materials Engineering (3mE) for acceptance a thesis entitled Human-Aware Autonomous Navigation of a Care Robot in Domestic Environments by

Map building is a classical problem in mobile and autonomous robotics, and sensor models is a way to interpret raw sensory information, especially for building maps. In this paper we propose a parameterized sensor model, and optimize map goodness with respect to these parameters. A new approach, measuring the goodness of maps without a handcrafted map of the actual environment is introduced and evaluated. Three different techniques; statistical analysis, derivative of images, and comparison of binary maps have been used as estimates of map goodness. The results show that the proposed sensor model generates better maps than a standard sensor model. However, the proposed approach of measuring goodness of maps does not improve the results as much as expected.

Artificial Intelligence (AI) and Machine Learning (ML) are playing transformative roles in process optimization within the context of Industry 4.0, driving improvements in efficiency, quality, and sustainability. The integration of Artificial Intelligence (AI) and Machine Learning (ML) into Industry 4.0 has revolutionized process optimization, enhancing productivity, efficiency, and flexibility in manufacturing systems. This review paper aims to provide an in-depth exploration of AI and ML techniques applied to process optimization within the context of Industry 4.0. It discusses various approaches, such as supervised and unsupervised learning, reinforcement learning, deep learning, and evolutionary algorithms, highlighting their applications in real-time monitoring, predictive maintenance, quality control, supply chain management, and process parameter optimization. The paper also examines the challenges and limitations faced when implementing these technologies, including data quality, system complexity, and integration issues. Furthermore, it presents case studies and industrial applications to demonstrate the practical impact of AI and ML-driven process optimization. The review concludes with a discussion on the future prospects of AI and ML in Industry 4.0, including advancements in smart manufacturing, digital twins, and the role of big data analytics in shaping next-generation manufacturing processes.

Meta-modeling for manufacturing processes describes a procedure to create reduced numeric surrogates that describe cause-effect relationships between setting parameters as input and product quality variables as output for manufacturing processes. Within this method, expert knowledge, empiric data and physical process models are transformed such that machine readable, reduced models describe the behavior of the process with sufficient precision. Three phases comprising definition, generation of data and creation of the model are suggested and used iteratively to improve the model until a required model quality is reached. In manufacturing systems, such models allow the generation of starting values for setting parameters based on the manufacturing task and the requested product quality. In-process, such reduced models can be used to determine the operating point and to search for alternative setting parameters in order to optimize the objectives of the manufacturing process, the product quality. This opens up the path to self-optimization of manufacturing processes. The method is explained exemplarily at the gas metal arc welding process.

The modern phase of science and technology evolution in the field of automatic and robotic systems is characterized by the use of multi-degree-of-freedom movement systems, realizing almost any spatial movements of an actuator or machining tool. Additional requirements for simultaneous implementation of all translational and angular motions are in increasing frequency demanded for new developed movement position devices. The multi-degree-of-freedom systems constructed on the basis of 6-DOF parallel mechanisms are among the most perspective solutions for such motions implementation. However, the task of rapid kinematic and dynamic analysis of such parallel mechanisms is one of the main difficulties in the sphere of robotics. Therefore the paper examines the simulation and analysis of two 6-DOF parallel mechanisms in MATLAB/Simulink development environment to present a productive and up-to-date way of similar robotic manipulators engineering. The 6-Dof Parallel Mechanisms The spatial m...

Path planning is an important task for mobileF service robots. Most of the available path-planning algorithms are applicable only in static environments. Achieving path planning becomes a difficult task in an unknown, dynamic environment. To solve the path planning problem in an unknown dynamic environment, this paper proposes a Bidirectional Rapidly-exploring Random Tree Star-Dynamic Window Approach (BRRT *-DWA) algorithm with Adaptive Monte Carlo Localization (AMCL). Bidirectional Rapidly-exploring Random Tree Star(BRRT *) is used to generate an optimal global path plan, Dynamic Window Approach(DWA) is a local planner and Adaptive Monte Carlo Localization(AMCL) is used as a localization technique. The robot can navigate using the map file of the unknown environment created by Simultaneous Localization And Mapping (SLAM) and the data from the Light Detection and Ranging (LiDAR) sensor while avoiding dynamic and static obstacles. In addition, the object identification algorithm You Only Look Once (YOLO) was adopted, trained, and used for the robot to recognize objects and people. Results obtained from both simulation and experiment show the proposed method can achieve better performance in a dynamic environment compared with other state-of-the-art algorithms.

Artificial intelligence (AI)-driven robotics is a rapidly evolving field that is transforming various industries, including healthcare, manufacturing, transportation, logistics, security, retail, agri-food, and construction. The integration of artificial intelligence algorithms and machine learning techniques has propelled robotics beyond mere automation, enabling machines to modify, alter, adjust, learn, and interact with the world in ways previously deemed science fiction. The relentless pursuit of creating intelligent robotic systems has led to a symbiotic relationship between human inventiveness and AI, with AI-driven autonomous cars, drones, and robots transforming transportation, healthcare, and exploration. It offers flexibility and learning capabilities, transforming the way machines interact with humans. The integration of AI and robotics marks a transformative era in which machines become companions and cognitive extensions of human capabilities. In the future, we expect AI-driven robotics to bring

Map building is a classical problem in mobile and autonomous robotics, and sensor models is a way to interpret raw sensory information, especially for building maps. In this paper we propose a parameterized sensor model, and optimize map goodness with respect to these parameters. A new approach, measuring the goodness of maps without a handcrafted map of the actual environment is introduced and evaluated. Three different techniques; statistical analysis, derivative of images, and comparison of binary maps have been used as estimates of map goodness. The results show that the proposed sensor model generates better maps than a standard sensor model. However, the proposed approach of measuring goodness of maps does not improve the results as much as expected.

The manufacturing sector has undergone a transformation due to additive manufacturing (AM), which makes it possible to create intricate, personalized items with little wastage of materials. However, the optimization and enhancement of AM processes remain a challenge due to the intricacies involved in design, material selection, and process parameters. This review explores the integration of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) techniques to improve and innovate within the field of AM. AI-driven design optimization procedures offer innovative solutions for 3-D printing of complex geometries and lightweight structures. By leveraging machine learning (ML) algorithms, these procedures analyze extensive data from previous manufacturing processes to enhance efficiency and productivity. ML models facilitate automation in design and production by learning from historical data and identifying intricate patterns that human operators might miss. Deep learning (DL) further augments this capacity by utilizing sophisticated neural networks to manage and interpret complex information, providing deeper insights into the manufacturing process. The integration of AI, ML, and DL into additive manufacturing enables the creation of optimized, lightweight components which are crucial for reducing fuel consumption in automotive and aviation industries. These advanced AI techniques not only optimize design and production processes but also enhance predictive modeling for process optimization and defect detection, leading to improved performance and reduced manufacturing costs. Therefore, integration of AI, ML, and DL into additive manufacturing not only improve precision in component fabrication, and enable advanced material design innovations but also opens up new possibilities for innovation in product design and material science. This review paper discusses and highlights significant advancements, and identifies future directions for the application of AI, ML, and DL in AM. By leveraging these technologies, the additive manufacturing processes can achieve unprecedented levels of precision, customization, and productivity in order to be analyzed and modified.

This paper focuses on studying the change technologies bring to increase operational performance across the various sectors of industries. The study adopts both quantitative and qualitative research methods. Information was collected by combining case studies, questionnaires, and interviews with specialists in the field, all of which allowed for a grounded investigation into the direct impact of technology on efficiency gains. The work explores future technologies, including AI, automation, and data analysis, by sharing data on the impact of these on cost, work output, and efficiency. The findings revealed that organizations implementing AI-based solutions in the SCM witnessed a significant decrease of 20% in operation cost and an enhancement in operation efficiency and decision-making. In addition, this study discusses the norms, including increased security threats and the continuous process of escalating the employee's skills (Smith et al., 2022). All these challenges are central to effectively introducing more technology in our organizations. Finally, the research reveals that, though technology has a significant impact on the delivery of effective services, one has to balance the availability of technology and investing in employee training programs that would need the technology in the long run. This balance is important to sustain competitive advantage and progressive enhancement of operational results.

Meta-modeling for manufacturing processes describes a procedure to create reduced numeric surrogates that describe cause-effect relationships between setting parameters as input and product quality variables as output for manufacturing processes. Within this method, expert knowledge, empiric data and physical process models are transformed such that machine readable, reduced models describe the behavior of the process with sufficient precision. Three phases comprising definition, generation of data and creation of the model are suggested and used iteratively to improve the model until a required model quality is reached. In manufacturing systems, such models allow the generation of starting values for setting parameters based on the manufacturing task and the requested product quality. In-process, such reduced models can be used to determine the operating point and to search for alternative setting parameters in order to optimize the objectives of the manufacturing process, the product quality. This opens up the path to self-optimization of manufacturing processes. The method is explained exemplarily at the gas metal arc welding process.

The development of modern technologies such as the Internet of Things (IoT), cloud computing, and artificial intelligence (AI) resulted in a new era of industrial automation and data interchange, which is known as Industry 4.0. AI-based decision support systems (DSS) play a crucial role in this paradigm by enhancing the integration and processing of IoT and sensor data to optimize operations, improve productivity, and enable predictive maintenance. Machine learning models analyze production data and visual inspections to identify defects and ensure product quality. This review paper explores the transformative role of AI in enhancing DSS within Industry 4.0, highlighting key technologies including machine learning, deep learning, and natural language processing. It explores a number of applications, including supply chain optimization, energy management, predictive maintenance, quality control, and production planning, showing how AI-driven DSS can significantly boost operational dependability, cut costs, and improve efficiency. The article also discusses the AI-based DSS's architecture and implementation, with a focus on data management, user interface design, and IoT integration. Furthermore, it examines the challenges related to data quality, technical integration, and human factors, offering potential solutions and strategies for effective deployment. The study highlights the continued development of AI technologies and their potential to support autonomous decision-making in industrial settings by identifying new trends and areas for further research. This comprehensive review aims to provide valuable insights for researchers and practitioners, fostering a deeper understanding of the capabilities and future potential of AI-based DSS in Industry 4.0.

In this paper, an open-source robot operating system called ROS is introduced. Unlike a traditional operating system that handles scheduling and process management, ROS provides a structured communication layer on top of the host operating system to facilitate communication among heterogeneous computing clusters. This paper explains how ROS can be leveraged to control objects remotely and safely like cars without human intervention. Additionally, the document outlines how ROS fits into the current robot software architecture and how it can be utilized for AUVs. The paper also presents a solution to inspect underground and underwater optical cables using a robotic operating system. To implement this solution, Ubuntu OS is virtually installed using VMWare Workstation, and ROS packages, including the ROS-Gazebo toolbox, are installed. The software is being tested using standard inputs, with light radiation used as the primary factor to assess the condition of the optical cable.

Optimal robotic grasping cannot be limited to the estimation of object grasping pose using vision-based methods. It is necessary to use tactile sensors to learn the physical properties of the objects that are to be grasped. In this work, we integrated two Contactile force-based tactile sensors with a 2F-140 ROBOTIQ gripper and a UR5 robot to estimate the volume of a waterfilled container using Multilayer Perceptron (MLP) neural networks. During experimentation, we trained and evaluated different
MLPs varying the input forces (Fx, Fy, Fz) in a task of discrete-volume regression in a range of between 0ml and 300ml. The preliminary proposed approach is compared with an algebraic method based on the diagram of the equilibrium of forces, proving that our results are more precise, obtaining a R2 value of 8% higher in the worst-case scenario, and of 30% in the best.

Map building is a classical problem in mobile and autonomous robotics, and sensor models is a way to interpret raw sensory information, especially for building maps. In this paper we propose a parameterized sensor model, and optimize map goodness with respect to these parameters. A new approach, measuring the goodness of maps without a handcrafted map of the actual environment is introduced and evaluated. Three different techniques; statistical analysis, derivative of images, and comparison of binary maps have been used as estimates of map goodness. The results show that the proposed sensor model generates better maps than a standard sensor model. However, the proposed approach of measuring goodness of maps does not improve the results as much as expected.

Complex system science has recently shifted its focus to include modeling, simulation, and behavior control. An effective simulation software built on robot operating system (ROS) is used in robotics development to facilitate the smooth transition between the simulation environment and the hardware testing of control behavior. In this paper, we demonstrate how the simultaneous localization and mapping (SLAM) algorithm can be used to allow a robot to navigate autonomously. The Gazebo is used to simulate the robot, and Rviz is used to visualize the simulated data. The G-mapping package is used to create maps using collected data from a variety of sensors, including laser and odometry. To test and implement autonomous navigation, a Turtlebot was used in a Gazebo-generated simulated environment. In our opinion, additional study on ROS using these important tools might lead to a greater adoption of robotics tests performed, further evaluation automation, and efficient robotic systems.

This paper reports some progress on the project KeJia, a long-term effort aiming at integrated intelligence for service robots. We focus in this paper on the high-level cognitive functions developed on our robot KeJia, including human-robot dialogue understanding, task planning, and automatic transformation of the knowledge and information extracted from human-robot dialogues and other sources in verbal languages into the planner. We have been testing these techniques and the integrated system in RoboCup@home league competitions, as well as other case-studies involving complex tasks, general purpose service with incomplete or erroneous information, acquiring and reasoning with causal knowledge, and learning to operate a microwave oven through reading the manual.

Presented work aims to develop an autonomous mobile service robot which is able to navigate from the source to destination along with G-mapping of the given unstructured environment and it is able to localize itself in the generated map by using SLAM technique. This helps the robot to plan an efficient path to navigate to the goal position along with avoiding the obstacle interference. This is achieved with the help of ROS navigation stack. Robotic Operating System(ROS) is a framework which has been used to manage the robot's operation, tasks, motion. The navigation of the robot is generally divided into global motion planning and local motion control to navigate and avoid the obstacle present in the generated path. In simulation 3D simulator GAZEBO has been used to simulate the environment and the robot. Simulated LIDAR is used to create the global map of the unknown environment which is analysed and compared with the actual environment using RViz Tool.

Robot navigation is a crucial step towards satisfying the requirements of the client ,which deals with an autonomous bot navigating It's way through the obstacles of the space designated "EDS 9-10", in order to identify the plants spread across. With respect to the subsystem of path planning and trajectory generation, a gazebo simulation with a RVIZ analysis was adopted for the purposes of preliminary analysis. The first step to make this viable, is to obtain a mapping of the environment with possible extensions of obstacles that could be present in the system. Once the world(i.e. the environment) is modelled, it needs to be mapped using the sensors on the bot to collect information about its surroundings as well as its own location. This report presents a robotic operating system (ROS) based on teleop navigation to map the environment and robotic navigation implementation of an autonomous design clinic (ADC) bot modelled as a turtlebot3 model: burger, which is similar in dimensions to the actual bot, equipped with a laser scanner and a camera. For autonomous mapping simultaneous localisation and mapping along with manual exploration (teleop) has been used to obtain a 2D map of the environment in Gazebo. The A* search algorithm has been used for the global planner , while the dynamic window approach is used for the local planner. The Gazebo simulated results provide validation to the competency of the modelled world and the proposed navigation algorithm.

Many people with disabilities find it difficult or even impossible to use traditional powered wheelchairs independently by manually controlling the devices. Intelligent wheelchairs are a very good solution to assist severely handicapped people who are unable to operate classical electrical wheelchair by themselves in their daily activities. This paper describes a development platform for intelligent wheelchairs called IntellWheels. The intelligent system developed may be added to commercial powered wheelchairs with minimal modifications in a very straightforward manner. The paper describes the concept and design of the platform and also the intelligent wheelchair prototype developed to validate the approach. Preliminary results concerning automatic movement of the IntellWheels prototype are also presented.

This paper concerns the optimization of a navigation system for a robot, by using simulations to arrive at an effective solution. In this paper we discuss the benefits and limitations of using a proportionalintegral-derivative (PID) controller, how to overcome its limitations when using PID for a navigation system. This paper also gives an overview of how the Robot Operating System (ROS) and the physics engine Gazebo is used to implement and collect quantitative data.

• to know how to use (run and launch) ROS nodes and packages; • to understand the messaging structure, including topics and services; • to know about some of the core modules of ROS, including the Gazebo simulator, ROSbags, MoveIt! and the navigation stack.

Map building is a classical problem in mobile and autonomous robotics, and sensor models is a way to interpret raw sensory information, especially for building maps. In this paper we propose a parameterized sensor model, and optimize map goodness with respect to these parameters. A new approach, measuring the goodness of maps without a handcrafted map of the actual environment is introduced and evaluated. Three different techniques; statistical analysis, derivative of images, and comparison of binary maps have been used as estimates of map goodness. The results show that the proposed sensor model generates better maps than a standard sensor model. However, the proposed approach of measuring goodness of maps does not improve the results as much as expected.

The project presents an implementation of a prototype for the autonomous vehicles with the Robot Operating System (ROS). The system utilizes turtlebot 3 for the navigation purpose. The aim of this work is to integrate the obstacle avoiding algorithm with path planning techniques to create a system that is able to navigate in given static environments. The software prototyping tool used is Robot Operating System. Robots and their applications evolved swiftly over decades, proving to be a great achievement in human history. Robotics are improving people's lives by assisting them in resolving challenges they face on a daily basis. As a result, they have a greater impact on our lives. The influence of robot use on our lives is undeniably beneficial in terms of saving time and effort. Robotics' constant advancement has created several growth potentials in industries, education, utility facilities, and health care.

This paper presents a state machine-based architecture, which enhances the flexibility and reusability of industrial robots, more concretely dual-arm multisensor robots. The proposed architecture, in addition to allowing absolute control of the execution, eases the programming of new applications by increasing the reusability of the developed modules. Through an easy-to-use graphical user interface, operators are able to create, modify, reuse and maintain industrial processes, increasing the flexibility of the cell. Moreover, the proposed approach is applied in a real use case in order to demonstrate its capabilities and feasibility in industrial environments. A comparative analysis is presented for evaluating the presented approach versus traditional robot programming techniques.

In the ever-evolving landscape of technology, the imperative for adaptive and selfoptimizing systems has become increasingly evident. This research endeavors to probe the intricate intersection of artificial intelligence, machine learning, and automation, specifically within the realm of platform engineering. By addressing the necessity for intelligent automation platforms capable of dynamic adaptation and self-optimization, this paper aims to elucidate their role in navigating the complexities of contemporary systems. Through an exploration of challenges, opportunities, and recent advancements, the research endeavors to offer a nuanced understanding of the pivotal role played by dynamic adaptation and self-optimization in shaping the trajectory of automation platforms. In this paper, we embark on a journey to investigate the multifaceted dimensions of dynamic adaptation and self-optimization, critically analyzing their implications for continuous improvement. With the pervasive integration of automation in diverse industries, conventional static approaches prove insufficient to contend with the dynamic and unpredictable nature of contemporary environments. The conceptualization of dynamic adaptation and self-optimization emerges as a crucial paradigm shift, signifying a departure from static frameworks towards intelligent systems that can not only react to changes but also autonomously enhance their efficiency over time. As the paper unfolds, the myriad challenges and opportunities associated with dynamic adaptation and self-optimization in platform automation are meticulously explored. Challenges span from the intricacies of managing real-time data to ensuring the stability of systems, with ethical considerations looming large. Simultaneously, opportunities manifest in the form of heightened efficiency, reduced downtime, and increased adaptability to unforeseen circumstances. This section provides a comprehensive examination of the intricate balance required to harness the potential benefits while mitigating the challenges posed by the integration of intelligent systems into automation platforms.

Mechanoluminescence is the phenomenon in which certain materials emit light when subjected to mechanical stimuli, such as bending, stretching, or compression. Soft devices containing embedded mechanoluminescent materials are capable of responding to mechanical deformation by emitting light, which can be utilized for various applications, including sensing, display, communication, and visual feedback. In this Perspective, we discuss recent advancements and emerging applications of mechanoluminescent materials for soft devices, with a focus on the remaining challenges in mechanoluminescent materials, such as performance, mechanism, synthesis, and device fabrication, that need to be addressed for developing advanced soft devices, and propose the potential solutions.

In this paper, we are checking the flexibility of a SLAM based mobile robot to map and navigate in an indoor environment. It is based on the Robot Operating System (ROS) framework. The model robot is made using gazebo package and simulated in Rviz. The mapping process is done by using the GMapping algorithm, which is an open source algorithm. The aim of the paper is to evaluate the mapping, localization, and navigation of a mobile robotic model in an unknown environment. Keywords—Gazebo; ROS; Rviz; Gmapping; laser scan; Navigation; SLAM; Robot model; Packages.

Wearable biosensors have demonstrated enormous potential in revolutionizing healthcare by providing real-time fitness tracking, enabling remote patient monitoring, and facilitating early detection of health issues. To better sense vital life signals, researchers are increasingly favoring wearable biosensors with flexible properties that can be seamlessly integrated with human tissues, achieved through the utilization of soft materials. Gallium (Ga)based liquid metals (LMs) possess desirable properties, such as fluidity, high conductivity, and negligible toxicity, which make them inherently soft and well-suited for the fabrication of flexible and wearable biosensors. In this article, we present a comprehensive overview of the recent advancements in the nascent realm of flexible and wearable biosensors employing LMs as key components. This paper provides a detailed exposition of the unique characteristics of Ga-based LM materials, which set them apart from traditional materials. Moreover, the state-ofthe-art applications of Ga-based LMs in flexible and wearable biosensors that expounded from six aspects are reviewed, including wearable interconnects, pressure sensors, strain sensors, temperature sensors, and implantable bioelectrodes. Furthermore, perspectives on the key challenges and future developing directions of

Soft and stretchable strain sensors have aroused great interest in research and engineering fields due to their promising application potential in many areas, including human-machine interface and healthcare monitoring. However, developing stable, strain-sensitive, and fatigue-resistant wearable strain sensors remains challenging. Herein, we report a low-cost strain-sensing glove based on a commercial nitrile glove and liquid metal as both sensing units and circuit/interconnects, with excellent response to strains and great stability in long-term use. The liquid metal sensing circuit is prepared by scraping the liquid metal slurry in situ on glove fingers, followed by soft silicone encapsulation. The whole process does not involve toxic chemicals, so no strict requirements on the operating environment are necessary. The strain-sensing glove is capable of real-time monitoring of finger gestures in a very sensitive and accurate way, which exhibits great application potential as a soft controller in manipulating the machine hand to achieve related human-machine interaction.

Endowing robots with multi-directional tactile sensing capabilities has long been a challenging task in the field of flexible electronics and intelligent robots. This paper reports a highly sensitive, flexible tactile sensor with an embedded-hair-in-elastomer structure, which is capable of decoupling normal stress and shear stress. The flexible tactile sensor is fabricated on a thin polyimide substrate and consists of four self-bending piezoresistive cantilevers in a cross-shaped configuration, which are embedded in an elastomer. The sensor can decouple the tactile information into a normal stress and a shear stress with simple summation and differencing algorithms, and the measurement error is kept within 3%. Moreover, the sensitivity and detection threshold of the sensor can be adjusted by simply changing the elastic material. As a demonstration, the flexible tactile sensor is integrated into a robotic manipulator to precisely estimate the weight of the grasped objects, which shows great potential for application in robotic systems.

Recent advances in soft sensor technology have pushed digital healthcare toward life-changing solutions. Data reliability and robustness can be realised by building sensor arrays that collect comprehensive biological parameter data from several points on the underlying organs simultaneously, a principle that is inspired by bioreceptors. The rapid growth of soft lithography and printing, three-dimensional (3D) printing, and weaving/knitting technologies has facilitated the low-cost development of soft sensors in the array format. Advances in data acquisition, processing, and visualisation techniques have helped with the collection of meaningful data using arrays and their presentation to users on personal devices through wireless communication interfaces. Local-or cloud-based data storage helps with the collection of adequate data from sensor arrays over time to facilitate reliable prognoses based on historical data. Emerging energy harvesting technologies have led to the development of techniques to power sensor arrays sustainably. This review presents developmental building blocks in wearable and artificial organ-based soft sensor arrays, including bioreceptor-inspired sensing mechanisms, fabrication methods, digital data-acquisition techniques, methods to present the results to users, power systems, and target diseases/conditions for treatment or monitoring. Finally, we summarise the challenges associated with the development of single and multimodal array sensors for advanced digital healthcare and suggest possible solutions to overcome them.

The robotic with integrated tactile sensors can accurately perceive contact force, pressure, vibration, temperature and other tactile stimuli. Flexible tactile sensing technologies have been widely utilized in intelligent robotics for stable grasping, dexterous manipulation, object recognition and human-machine interaction. This review presents promising flexible tactile sensing technologies and their potential applications in robotics. The significance of robotic sensing and tactile sensing performance requirements are first described. The commonly used six types of sensing mechanisms of tactile sensors are briefly illustrated, followed by the progress of novel structural design and performance characteristics of several promising tactile sensors, such as highly sensitive pressure and tri-axis force sensor, flexible distributed sensor array, and multi-modal tactile sensor. Then, the applications of using tactile sensors in robotics such as object properties recognition, grasping and manipulation, and human-machine interactions are thoroughly discussed. Finally, the challenges and future prospects of robotic tactile sensing technologies are discussed. In summary, this review will be conducive to the novel design of flexible tactile sensors and is a heuristic for developing the next generation of intelligent robotics with advanced tactile sensing functions in the future.