Claim Missing Document
Check
Articles

Found 2 Documents
Search

Design and Integration of a Robotic Welding Parameterized Procedure for Industrial Applications Puthussery, Sangeeth; Secco, Emanuele Lindo
Spektrum Industri Vol. 22 No. 1 (2024): Spektrum Industri - April 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/si.v22i1.179

Abstract

This paper explores the development of an effective motion planning strategy for robotics welding in tube to tubesheet joints, a critical process in heat exchanger manufacturing. The research methodology follows an experimental paradigm, investigating two distinct approaches to tackle the intricacies of this task. The initial approach, involving a welding torch affixed to the robotic arm's flange, proved ineffective due to the complexity of continuous 360° orbital welding. This led to the adoption of a custom end effector in the second approach, designed to enhance adaptability and precision. Key tools and materials employed in this research include the Robot Operating System (ROS), Rviz for 3D visualization, MoveIt for motion planning, SolidWorks for CAD modelling, and the xArm7 Robotic Arm. These tools facilitated the creation of a comprehensive planning environment. The motion planning process relies on three essential parameters: tube diameter, type of tube to tubesheet joint (flush or protruding), and the 3D coordinates of tube centers. A Python scripts control the robot's movements, with specific joint state and pose goals for precise positioning. Finally, this study contributes to present a program that orchestrates the robotic arm's motion, simulating the welding process for tube to tubesheet joints. This comprehensive research endeavor contributes to the optimization of motion planning strategies in the context of tube to tubesheet welding, with practical applications in the manufacturing industry.
A Low-Cost Vision-based Fruit Sorting System for Robotic Applications Afaq, Muhammad; Secco, Emanuele Lindo
Scientific Journal of Engineering Research Vol. 2 No. 3 (2026): September (in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i3.2026.471

Abstract

Modern robotic systems address complex engineering challenges using artificial intelligence and machine learning techniques. In agricultural robotics, fruit identification and sorting remain challenging due to variations in size, shape, color, orientation, and lighting conditions. This study presents the design and implementation of a vision-based fruit sorting robotic system integrating YOLOv8-based object detection with robotic manipulation. A custom dataset consisting of images of 2 different fruits (namely banana and strawberry images), including single-fruit and multi-fruit scenarios, was used and manually annotated using bounding boxes in CVAT. The dataset was divided into training, validation, and test subsets to enable robust model development under realistic operational conditions. A lightweight YOLOv8 model was trained using CUDA acceleration and optimized for edge deployment by selecting YOLOv8n to balance inference speed and detection accuracy. The trained model was converted to ONNX format and deployed on a Raspberry Pi 5 for real-time inference using live camera input. Evaluation on an independent test dataset achieved a precision of 0.999, recall of 1.000, mAP@0.5 of 0.995, and mAP@0.5:0.95 of 0.963 under controlled experimental conditions with limited object classes. The modular architecture enables low-cost and scalable deployment and provides a foundation for future enhancements, including closed-loop robotic control, additional object categories, and operation in more dynamic environments.