کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6939727 | 1449973 | 2018 | 32 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Active garment recognition and target grasping point detection using deep learning
ترجمه فارسی عنوان
شناختن لباس های فعال و شناسایی نقطه هدف با استفاده از یادگیری عمیق
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
طبقه بندی پوشاک، لباس پوشیدن، یادگیری عمیق، تصاویر عمیق
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
چشم انداز کامپیوتر و تشخیص الگو
چکیده انگلیسی
Identification and bi-manual handling of deformable objects, like textiles, is one of the most challenging tasks in the field of industrial and service robotics. Their unpredictable shape and pose makes it very difficult to identify the type of garment and locate the most relevant parts that can be used for grasping. In this paper, we propose an algorithm that first, identifies the type of garment and second, performs a search of the two grasping points that allow a robot to bring the garment to a known pose. We show that using an active search strategy it is possible to grasp a garment directly from predefined grasping points, as opposed to the usual approach based on multiple re-graspings of the lowest hanging parts. Our approach uses a hierarchy of three Convolutional Neural Networks (CNNs) with different levels of specialization, trained both with synthetic and real images. The results obtained in the three steps (recognition, first grasping point, second grasping point) are promising. Experiments with real robots show that most of the errors are due to unsuccessful grasps and not to the localization of the grasping points, thus a more robust grasping strategy is required.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Pattern Recognition - Volume 74, February 2018, Pages 629-641
Journal: Pattern Recognition - Volume 74, February 2018, Pages 629-641
نویسندگان
Enric Corona, Guillem Alenyà , Antonio Gabas, Carme Torras,