This paper not only explores the fundamental aspects of but also brings new ideas for maintenance, repair, and overhaul (MRO) operations of robotic systems (RS). This synthesis is based on the limited scholarly research in this area and on information gathered from comprehensive web searches and analysis of corporate websites so that the results reflect the current views of RS developers and operators. The paper describes several crucial areas concerning RS MRO: maintenance of robotic systems, challenges and best practices for RS MRO, predictive maintenance variables and key performance indicators, data analytics, software solutions for RS MRO, and logistics/supply chain approach that should be considered. These insights provide not only a comprehensive understanding of the current state of RS MRO but also describe trends and suggestions for the future of RS MRO, emphasizing the novelty of the proposed research conducted. Key trends that organizations will need to address include the use of artificial intelligence (AI) models and the increasing importance of RS MRO logistics and supply chain management.
This paper presents an integrative review of control strategies in robotics, covering classical control methods (linear quadratic regulator, proportional-integral-derivative), modern methods (adaptive, sliding mode, model predictive, and H-infinity), intelligent control methods (neural network, fuzzy logic, and machine learning), and hybrid control methods (integration of classical, modern, and intelligent control methods) to identify the advantages, limitations and gaps for future. A brief comparison of control methods between the types of control strategies is conducted with respect to robustness, stability, and complexity of implementation on 3 different levels of evaluation criteria: high, average, and low; advantages; limitations; and robotic applications, including examples. This paper discusses the theoretical and practical advancements and the classification of control strategies according to controller types (linear, nonlinear, and learning-based), approaches (model-based and model-free), and classifications (centralized, decentralized, and modal control). The review highlights the strengths, limitations, and potential research directions in bridging classical, modern, intelligent, and hybrid control paradigms to achieve safe, efficient, and adaptive robotic behavior in complex, uncertain environments. We discuss the future direction: autonomy, human-robot collaboration, and enhanced learning and challenges: cost, reliability, safety of control strategies, concluding with recommendations for future research.
Wheeled mobile robots (WMR) are unmanned vehicles and practical robots for industry and human life. The low-cost manufacturing, simple assembling, high-speed, lightweight design, and high observability and controllability of the WMRs have attracted the attention of engineering disciplines such as mechanical and electrical science. This paper focuses on the control of wheeled mobile robots through fuzzy adaptive back stepping (ABS). The mathematical model of WMR is divided into two types, including kinematic and dynamic analyses. Actually, this research analyzes the theoretical math model using hybrid methods such as fuzzy logic and adaptive back stepping (BS) to control WMR in both noisy and noiseless conditions along its path. On the other hand, this hybrid controller, because of its more robust performance, can track WMR on its targets. Because of this, WMR's ability to move around makes it choose fuzzy and adaptive back stepping (FABS) methods, which use model-based and time-dependent features, respectively. As a result, the signal inputs fuzzy membership functions, and then the fuzzy approach outputs a new signal that goes to the back-step adaptive controller to finalize the control effort to navigate WMR with the lowest error during its destinations.
Delta robots play a critical role in high-speed industrial applications due to their parallel kinematic structure, which provides superior precision, agility, and efficiency. This study presents a reconfigurable Delta robot with a novel structural adaptation mechanism, allowing geometric modifications to optimize its kinematic and dynamic performance. The research systematically derives the robot’s kinematic and dynamic equations, examines the impact of altering the structure of its chains, and applies genetic algorithm optimization to enhance its overall functionality. The influence of varying arm lengths, chain structures, and joint configurations is analyzed to determine their effects on workspace, actuator torque requirements, and operational stability. The findings indicate that optimized chain configurations improve workspace utilization by up to 15 %, reduce actuator torque by 12 %, and enhance end-effector speed by 8 %. By integrating structural adaptability and optimization techniques, this study demonstrates that the reconfigurable Delta robot achieves a superior balance between precision, speed, and energy efficiency. These advancements make it a promising solution for next-generation high-speed robotic applications in industries such as packaging, assembly, and medical automation.
Aiming at the problem of poor part recognition due to mutual occlusion between parts and the influence of different postures in the assembly scene, we propose an improved Mask R-CNN-based part recognition method for complex scenes. Firstly, the ResNet101 network is used to enhance the feature extraction capability of the network and improve the part recognition effect; secondly, the normalization layer of the backbone network is replaced to reduce the effect of batch size on the feature extraction of the model; lastly, the feature pyramid network structure is improved to enhance the transfer efficiency between the high and low layers of the network, and to enhance the capability of the feature capture; through the experiments on the homemade dataset, the average detection accuracy of this method is 4.7 % higher than that of the original Mask R-CNN. Through the experiments on the homemade dataset, it is found that compared with the original Mask R-CNN, the average detection accuracy of the method is improved by 4.7 %.The optimized network model proposed in this paper can improve the accuracy of part recognition, realize the accurate detection of parts in the complex environment such as stacking, occlusion and so on, and provide a solution for the recognition of parts in the complex environment.
