Mekatronika: Journal of Intelligent Manufacturing and Mechatronics

Utilization of Mediapipe Posture Recognition for the Usage in Estimating ASD Children Engagement Interacting with QTrobot

2024-06-23T15:40:43+00:00

Imitation skills are one of the most important learning skills that are naturally developed by typically developed (TD) children at a young age. Unfortunately, this skill is lacking in special children who are diagnosed with Autism Spectrum Disorder (ASD). To enhance the ASD children’s imitation skills for a better social life, this paper proposes to develop and embed a robust gesture recognition system onto a therapy robot called QTrobot. This paper will discuss the utilization of Mediapipe posture recognition as part of estimating the ASD children engagement. MediaPipe posture recognition has the average accuracy of 96% and 60% for both straight facing the camera and 60 degrees away from the camera, respectively. Further enhancements have been done to embed the selected gesture recognition algorithm into QTrobot for developing an efficient Human-Robotic interaction (HRI). Using twenty healthy adult participants, the enhanced algorithm has achieved an average of 94.33% accuracy with an average of 10.5 frame rates per second in recognizing five selected gestures to be imitated by the participants, which are T pose, Strong pose, Super pose, Victory pose, and V pose. Plus, the participants experienced a useful and enjoyable interaction with the robot based on a the 5-point Likert scale of the Technology Acceptance Model (TAM) questionnaire.

Design of Automatic Tekong Launcher System Using Progressive Methods

2024-06-23T15:45:29+00:00

The Automatic Tekong Launcher System represents a cutting-edge advancement in sepak takraw equipment, seamlessly blending precision engineering with advanced automation to transform the role of the Tekong. At its foundation, the system is built from durable aluminum profiles, ensuring a robust and reliable structure. The launcher mechanism is crafted using CNC milling technology, reflecting a commitment to precision and optimal performance. Central to the system’s operation is a power supply, featuring three 30A AC to DC converters that provide consistent electricity to the motors. These motors include four high-speed 24V DC units and two stepper motors, capable of reaching speeds up to 2800 rpm. This setup allows for meticulous control over the ball's speed and trajectory, essential for precise launches. The brain of the system is a Programmable Logic Controller (PLC), which manages the intricate movements of both motors and sensors, enabling the automation of ball launching with minimal human intervention. For added versatility, the system incorporates joystick control, allowing for semi-automatic operation that enhances user interaction and adaptability to various gameplay scenarios. By integrating advanced automation, precision engineering, and a modular design, the Automatic Tekong Launcher System offers unparalleled performance in both training and competitive environments. Its ability to deliver consistent, accurate launches elevates the standard of sepak takraw, making it a revolutionary tool for players and coaches aiming to refine their skills and strategies.

Dynamic Target Grasping Strategy Of Industrial Robot Based On Machine Vision

2024-08-27T02:59:42+00:00

Object grasping is the predominant application focus of robots, with machine vision technology playing a crucial role in enabling successful grasping. As research on machine vision technology advances, its initial application in capturing static targets has gradually expanded to include tracking and capturing moving targets. Detecting the target position is a common method for estimating and predicting its motion state, allowing for stable capture of moving targets. However, if the target's position changes unexpectedly due to interference, the original predicted position becomes invalid. Therefore, continuous localization and tracking of the target are necessary to assess deviations and approach the new target position in order to achieve successful capture. In this study, we utilize ROS as a platform to investigate dynamic grasping strategies based on visual feedback. We construct a dynamic grasping system using an UR5 industrial robot within ROS framework. The RealSense D435i camera is mounted at the end effector of the robot arm in an Eye-in-Hand configuration to obtain RGB-D image data representing the field of view at execution end point. By performing coordinate conversion, we acquire three-dimensional coordinates of objects in relation to base coordinate system of industrial robot. A visual feedback control strategy is designed to facilitate grasping operations on moving targets located on conveyor belts.When the target moved along the conveyor belt at a speed of 10mm/s, the camera realized accurate recognition of the object position, and the error was controlled within 1mm. At the same time, the industrial robot grasps and tracks the position error below 2mm to complete the target grasp.