Abstract
Laser-based additive manufacturing (LAM) offers the ability to produce near-net-shape metal parts with unparalleled energy efficiency and flexibility in both geometry and material selection. Despite advantages, these processes are inherently, as they are characterized by multiphysics interactions, multiscale phenomena, and highly dynamic behaviors, making their modeling and optimization particularly challenging. Artificial intelligence (AI) has emerged as a promising tool for enhancing the monitoring and control of additive manufacturing. This paper presents a systematic review of AI applications for real-time control of laser-based manufacturing processes, analyzing 16 relevant articles sourced from Scopus, IEEE Xplore, and Web of Science databases. The primary objective of this work is to contribute to the advancement of autonomous manufacturing systems capable of self-monitoring and self-correction, ensuring optimal part quality, enhanced efficiency, and reduced human intervention. Our findings indicate that 62.5 % of the 16 analyzed studies have deployed AI-driven controllers in real-world scenarios, with over 56 % using AI for control strategies, such as Reinforcement Learning. Furthermore, 62.5 % of the studies employed AI for process modeling or monitoring, which was integral to the development or data pipelines of the controllers. By defining a groundwork for future developments, this review not only highlights current advancements but also hints future innovations that will likely include AI-based controllers.

Abstract
Precision agriculture seeks to optimize crop yields while minimizing resource use. A key challenge is achieving uniform pesticide spraying to prevent crop damage and environmental contamination. Water-sensitive paper (WSP) is a common tool used for assessing spray quality, as it visually registers droplet impacts through color change. This work introduces a smartphone-based solution for capturing WSP images within vegetation, offering a tool for farmers to assess spray quality in real-world conditions. To achieve this, two approaches were explored: classical computer vision techniques and machine learning (ML) models (YOLOv8, Mask-RCNN, and Cellpose). Addressing the challenges of limited real-world data and the complexity of manual annotation, a programmatically generated synthetic dataset was employed to enable sim-to-real transfer learning. For the task of WSP segmentation within vegetation, YOLOv8 achieved an average Intersection over Union of 97.76%. In the droplet detection task, which involves identifying individual droplets on WSP, Cellpose achieved the highest precision of 96.18%, in the presence of overlapping droplets. While classical computer vision techniques provided a reliable baseline, they struggled with complex cases. Additionally, ML models, particularly Cellpose, demonstrated accurate droplet detection even without fine-tuning.

Abstract
Directed Energy Deposition (DED) is a free-form metal additive manufacturing process characterized as toolless, flexible, and energy-efficient compared to traditional processes. However, it is a complex system with a highly dynamic nature that presents challenges for modeling and optimization due to its multiphysics and multiscale characteristics. Additionally, multiple factors such as different machine setups and materials require extensive testing through single-track depositions, which can be time and resource-intensive. Single-track experiments are the foundation for establishing optimal initial parameters and comprehensively characterizing bead geometry, ensuring the accuracy and efficiency of computer-aided design and process quality validation. We digitized a DED setup using the Robot Operating System (ROS 2) and employed a thermal camera for real-time monitoring and evaluation to streamline the experimentation process. With the laser power and velocity as inputs, we optimized the dimensions and stability of the melt pool and evaluated different objective functions and approaches using a Response Surface Model (RSM). The three-objective approach achieved better rewards in all iterations and, when implemented in areal setup, allowed to reduce the number of experiments and shorten setup time. Our approach can minimize waste, increase the quality and reliability of DED, and enhance and simplify human-process interaction by leveraging the collaboration between human knowledge and model predictions.

Abstract
This paper compares five PID controller architectures for robotic manipulator position control, addressing the challenge of maintaining performance under varying inertial loads while providing accessible implementations for research and education. The five PID controller architectures for a three degrees-of-freedom SCARA manipulator position control are a basic Proportional-Derivative (PD), PD with Feed-Forward (FF), Parallel PD-PI-FF, Cascade PD-PI-FF, and Cascade PD-PI-FF with dead zone (DZ) compensation. The controllers were evaluated under varying inertial loads to assess robustness, extending beyond previous work's idealized conditions. Results show advanced configurations reduced errors by up to 64% compared to the baseline PD, with Parallel-FF achieving optimal dynamic performance and Cascade-FF-DZ excelling in steady-state control. The Feed-Forward addition enhanced tracking performance, while DZ compensation effectively eliminated limit cycles. The work provides open-source implementations and simulation environments, supporting research reproducibility and educational applications in robotics control.

Abstract
Integrating physical robots in an educational context often entails acquiring expensive equipment that often operates using proprietary software. Both conditions restrict the students from exploring and fully understanding the internal operation of robots. In response to these limitations, a three-degree-of-freedom robotic manipulator, based on the “EEZYbotARM MK2” open-source design by Carlo Franciscone, is being repurposed and integrated within the SimTwo simulation environment to operate within a hardware-in-the-loop architecture. To accomplish this objective, first, an open-source Arduino-based library was developed aiming at the robot’s online and offline programming akin to industrial robots. The firmware is able to communicate with the SimTwo software in which the digital twin’s robot is living. The dynamic behavior of the robot’s digital twin must be properly parametrized and aligned with the physical robot’s dynamics. This article describes the modeling of the robot joint’s actuator and its closed-loop controller formulation. The obtained results show that the dynamic behavior of the robot joint digital twin closely matches both open and closed-loop, the one of its physical counterpart.

Abstract
Force sensors are essential elements of actuator systems, providing measurement and force control in different domains. This literature review discusses its applications in the industry, academic research, and educational domains. In an industrial setup, force sensors enhance efficiency, safety, and reliability within automation systems, predominantly robotic arms and assembly lines. In the academic environment, using such sensors fosters innovation within robotics and biomechanical studies, allowing for testing theoretical models and new methodologies. In education, force sensors help students understand basic concepts about mechanics and robotics from practical work. Understanding this diverse application allows one to design effective actuator systems, promoting technological advances and improved learning experiences. With this literary review, the aim is to gain an understanding of the state of the art in force sensor actuators applied in various areas, such as academia, education, and industry.