کنفرانس مهندسی برق ایران

صفحه اصلی / سی و دومین کنفرانس بین المللی مهندسی برق

Scene Understanding in Pick-and-Place Tasks: Analyzing Transformations Between Initial and Final Scenes

نویسندگان :

Seraj Ghasemi¹ Hamed Hosseini² MohammadHossein Koosheshi³ Mehdi Tale Masouleh⁴ Ahmad Kalhor⁵

1- University of Tehran 2- دانشگاه تهران 3- دانشگاه تهران 4- University of Tehran 5- University of Tehran

کلمات کلیدی :

Scene Understanding،Convolutional Neural Networks،Object Detection،Pick-and-Place،YOLOv5

چکیده :

With robots increasingly collaborating with humans in everyday tasks, it is important to take steps toward robotic systems capable of understanding the environment. This work focuses on scene understanding to detect pick-and-place tasks given initial and final images from the scene. To that end, a dataset is collected for object detection and pick-and-place task detection. A YOLOv5 network is subsequently trained to detect the objects in the initial and final scenes. Given the detected objects and their bounding boxes, two methods are proposed to detect the pick-and-place tasks that transform the initial scene into the final scene. A geometric method is proposed that tracks objects' movements in the two scenes and works based on the intersection of the bounding boxes that moved within scenes. Contrarily, the CNN-based method utilizes a Convolutional Neural Network to classify objects with intersected bounding boxes into 5 classes, showing the spatial relationship between the involved objects. The performed pick-and-place tasks are then derived from analyzing the experiments with both scenes. Results show the CNN-based method outscores the geometric method by roughly 12\% in certain scenarios, with an overall success rate of 84.3\%.