Determination of Angular Status and Dimensional Properties of Objects for Grasping with Robot Arm

Ucar, Kursad; Koçer, Hasan Erdinç

doi:10.1109/tla.2023.10015227

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(15) The work described in Ref. 16 shows the deployment of a two-dimensional (2D) camera and the application of YOLO to detect objects on a running conveyor belt with a constant speed on a frame-by-frame basis. In Ref.…”

Section: Introductionmentioning

confidence: 99%

Vision-based Robotic Arm Control for Screwdriver Bit Placement Tasks

Lin,

Shih

2024

Sensors and Materials

View full text Add to dashboard Cite

Robotic arms are widely used in the automation industry to package and deliver classified objects. When the products are small objects with very similar shapes, such as screwdriver bits with slightly different threads, pointed tips, and thicknesses, object selection and assembly often lead to misjudgment. We have developed a practical robotic arm control system based on vision detection techniques for screwdriver bits' placement. In addition to effectiveness, easy deployment and high flexibility in the field are also taken into account. The vision-based system consists of four processing stages in the following order: world coordinate conversion from image pixel coordinates, object detection, edge detection, and object orientation. In the first stage, a manual two-point marking method is proposed to easily configure the coordinate conversion for robot operating system (ROS)-based manipulators. For the following stages, we focus on the fine integration of state-of-the-art methods for the technical feasibility of the screwdriver bit placement. Such integration includes the selection between object detection methods and the data flow control among system stages. The experimental results show that (1) in detecting screwdriver bits, You Only Look Once (YOLO) v4 outperforms YOLOv7 and Single Shot MultiBox Detector at an accuracy rate of 99.51%; (2) in the edge detection, the object detection output can better illustrate the object contour than a whole image, achieving a mean absolute error of 0.86% in estimating the object angle; and (3) a successful real-time replacement rate of 96% is achieved for 12 screwdriver bits randomly scattered on a conveyor belt.

show abstract

Section: Introductionmentioning

confidence: 99%

Vision-based Robotic Arm Control for Screwdriver Bit Placement Tasks

Lin,

Shih

2024

Sensors and Materials

View full text Add to dashboard Cite

show abstract

Robot arm grasping based on YOLOv5 in the perspective of automated production

Wang

2024

Eng. Res. Express

View full text Add to dashboard Cite

The rapid development of industrial intelligence has gradually expanded the application of automated production. As a typical automated production equipment, the robotic arm still faces the problems of low grasping efficiency and high control costs when facing highly integrated and miniaturized components. Given this, to improve the grasping level of the robotic arm in complex production environments, this study first constructs a kinematic mathematical model of the robotic arm. Secondly, based on the algorithm that You Only Look Once, improvements are made to its convolution operation and feature extraction modules, ultimately proposing a new type of robotic arm grasping control model. The results showed that the loss test value of the new model was the lowest at 2.75, the average detection error of the captured object was the lowest at 0.003, and the average detection time was the shortest at 1.28 seconds. The highest success rate for grasping six types of industrial parts was 94%, and the lowest average energy consumption was 35.67 joules. Therefore, research models can significantly improve the grasping performance of robotic arms under various complex conditions, thereby achieving efficient manipulation of robotic arms in industrial automation.

show abstract

An Approach to Improve Object Detection with You Only Look Once (YOLO) and Artificial Neural Networks

Ucar

2024

2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP)

View full text Add to dashboard Cite

Determination of Angular Status and Dimensional Properties of Objects for Grasping with Robot Arm

Cited by 3 publications

References 0 publications

Vision-based Robotic Arm Control for Screwdriver Bit Placement Tasks

Vision-based Robotic Arm Control for Screwdriver Bit Placement Tasks

Robot arm grasping based on YOLOv5 in the perspective of automated production

An Approach to Improve Object Detection with You Only Look Once (YOLO) and Artificial Neural Networks

Contact Info

Product

Resources

About