This study aims to develop systematic research about augmented reality (AR) problems, challenges, and benefits in the current applications of five fields of interest. Articles were selected from scientific, technical, academic, and medical databases of digital journals and open access papers about AR. Therefore, the method used to develop the investigation was PRISMA, which allowed us to observe interesting facts and coincidences about complexities and successful cases of AR implementation in the disciplines of education, marketing, medicine, entertainment, and industry. The summary provided in this study was the result of the exploration of 60 recent articles found and selected by relevance using the PRISMA method. The main objective of this paper is to orient and update researchers regarding current applications, benefits, challenges, and problems in AR implementation for future studies and developments.

Space assets like communication satellites, space telescopes, and microgravity research stations are essential for human knowledge development. Nevertheless, space assets are subject to failure, damage, or obsolescence in their life cycle. A space asset's failure, damage, or obsolescence is typically addressed using teleoperated space robot systems to diagnose, repair, or upgrade it. In these activities, the region of interest or components to be serviced may be visually occluded by light or a physical obstacle, complicating the teleoperated maneuver and compromising the mission's success and safety as a collision may occur due to blind spots generated by visual occlusions. This paper presents an Augmented Reality (AR)-based robotic framework that allows the robot to perform an on-orbit servicing task despite visually occluded areas. It allows the user to dynamically obtain the best view in a 3D (three-dimensional) model. Besides, for the robot tool to accurately reproduce the natural motion of a human operator's hand, a direct handpresence device is used to directly map the avatar's hand motion to the robot’ send-effector(EE) motion. The system is validate din an AR environment with virtual and physical entities to repair a spacecraft's solar panel in a visually occluded area for the robot. The experimental results demonstrate that because the virtual environment can be manipulated in real-time to show the best perspective to the human operator, the repair trajectory was generated without compromising the safety and operations, even though the robot's EE and the camera-in-hand were not able to observe the area of interest directly.

A multi-agent system (MAS) is suitable for addressing tasks in a variety of domains without any programmed behaviors, which makes it ideal for the problems associated with the mobile robots. Reinforcement learning (RL) is a successful approach used in the MASs to acquire new behaviors; most of these select exact Q-values in small discrete state space and action space. This article presents a joint Q-function linearly fuzzified for a MAS’ continuous state space, which overcomes the dimensionality problem. Also, this article gives a proof for the convergence and existence of the solution proposed by the algorithm presented. This article also discusses the numerical simulations and experimental results that were carried out to validate the proposed algorithm.

Teleoperation provides an innovative approach for completing tasks in environments where humans cannot be physically present, such as hazardous or difficult-to-reach areas. Augmented Reality (AR) enhances this process by overlaying critical information directly into the user’s field of view, streamlining task execution and spatial awareness. This paper presents a comprehensive survey of recent trends in both teleoperation and AR, highlighting their integration to improve remote human-machine interaction. We analyze advancements in both technologies, identify practical applications, and offer insights into their convergence in fields such as aerospace, medical robotics, and industrial automation. By examining academic publications and statistical trends from major databases, we project the future trajectory of AR-teleoperation and discuss potential challenges in implementing these systems, particularly regarding latency, cognitive overload, and security. This survey aims to provide a detailed analysis of the state of the art and offers insights for future research in this rapidly evolving field.

Partial shading conditions reduce the efficiency of photovoltaic (PV) systems by introducing multiple local maxima in the power–voltage curve, complicating Maximum Power Point Tracking (MPPT). Traditional MPPT methods, such as Perturb and Observe (P&O) and Incremental Conductance (IC), frequently converge to local maxima, leading to suboptimal power extraction. This study proposes a hybrid reinforcement learning-based MPPT approach that combines fuzzy techniques with Deep Deterministic Policy Gradient (DDPG) to enhance tracking accuracy under partial shading. The method integrates fuzzy membership functions into the actor–critic structure, improving state representation and convergence speed. The proposed algorithm is evaluated in a simulated PV environment under various shading scenarios and benchmarked against conventional Perturb and Observe P&O and IC methods. Experimental results demonstrate that the Fuzzy–DDPG approach outperforms these classical techniques by achieving a higher tracking efficiency of 95%, compared to 85% for P&O and 88% for IC in average, while also minimizing steady-state oscillations. Additionally, the proposed method reduces tracking errors by up to 7.9% compared to conventional MPPT algorithms. These findings indicate that the combination of fuzzy logic and deep reinforcement learning provides a more adaptive and efficient MPPT solution, ensuring improved energy harvesting in dynamically changing conditions.