Robots are increasingly utilized in manufacturing and logistics, where bin-picking has become crucial for managing randomly placed objects. However, traditional methods often rely on expensive 3D vision systems, have limited adaptability to unstructured environments, and primarily focus on the picking process, neglecting the placing tasks. To address these challenges, this study presents a cost-effective system that combines a depth camera, YOLO-based instance segmentation, and optimization-based inverse kinematics for real-time object detection and stable manipulation. In the placing stage, an adaptive algorithm detects empty tray holes and generates grid patterns, ensuring reliable placement even in the presence of tray misalignments, occupied slots, or partial occlusions. Experimental validation revealed a 91% success rate in mixed-object environments during picking tasks and a 94% success rate for placing tasks, even with tray displacement and occlusion conditions. The results demonstrate that the system maintains stable performance across both picking and placing processes while minimizing reliance on expensive hardware and complex initial setups. By enhancing flexibility and scalability, the proposed approach offers a practical solution for intelligent automation and can serve as a foundation for broader applications in assembly, logistics, and service robotics.

This study developed a defect-detecting system for automotive wheel nuts. We proposed an image processing method using OpenCV for efficient defect-detection of automotive wheel nuts. Image processing method focused on noise removal, ratio adjustment, binarization, polar coordinate system formation, and orthogonal coordinate system conversion. Through data collection, preprocessing, object detection model training, and testing, we established a system capable of accurately classifying defects and tracking their positions. There are four defect types. Types 1 and 2 defects are defects of products where the product is completely broken circumferentially. Types 3 and 4 defects are defects are small circumferential dents and scratches in the product. We utilized Faster R-CNN and YOLOv8 models to detect defect types. By employing effective preprocessing and post-processing steps, we enhanced the accuracy. In the case of Fast RCNN, AP values were 0.92, 0.93, 0.76, and 0.49 for types 1, 2, 3, and 4 defects, respectively. The mAP was 0.77. In the case of YOLOv8, AP values were 0.78, 0.96, 0.8, and 0.51 for types for types 1, 2, 3, and 4 defects, respectively. The mAP was 0.76. These results could contribute to defect detection and quality improvement in the automotive manufacturing sector.

Recently, in-depth studies on sensors of autonomous vehicles have been conducted. In particular, the trend to pursue only camera-based autonomous driving is progressing. Studies on object detection using IR (Infrared) cameras is essential in overcoming the limitations of the VIS (Visible) camera environment. Deep learning-based object detection technology requires sufficient data, and data augmentation can make the object detection network more robust and improve performance. In this paper, a method to increase the performance of object detection by generating and learning a high-resolution image of an infrared dataset, based on a data augmentation method based on a Generative Adversarial Network (GAN) was studied. We collected data from VIS and IR cameras under severe conditions such as snowfall, fog, and heavy rain. The infrared data images from KAIST were used for data learning and verification. We confirmed that the proposed data augmentation method improved the object detection performance, by applying generated dataset to various object detection networks. Based on the study results, we plan on developing object detection technology using only cameras, by creating IR datasets from numerous VIS camera data to be secured in the future and fusion with VIS cameras.