Real-time robotic grasping and localization using deep learning-based object detection technique

This work aims to increase the impact of computer vision on robotic positioning and grasping in industrial assembly lines. Real-time object detection and localization problem is addressed for robotic grasp-and-place operation using Selective Compliant Assembly Robot Arm (SCARA). The movement of SCAR...

Full description

Bibliographic Details
Main Authors:	Farag, Mohannad, Abdul Nasir, Abd Ghafar, Alsibai, Mohammed Hayyan
Format:	Conference or Workshop Item
Language:	English
Published:	IEEE 2019
Subjects:	TK Electrical engineering. Electronics Nuclear engineering
Online Access:	http://umpir.ump.edu.my/id/eprint/25004/ http://umpir.ump.edu.my/id/eprint/25004/ http://umpir.ump.edu.my/id/eprint/25004/7/Real-Time%20Robotic%20Grasping%20and%20Localization1.pdf

id	ump-25004
recordtype	eprints
spelling	ump-250042019-12-02T08:15:58Z http://umpir.ump.edu.my/id/eprint/25004/ Real-time robotic grasping and localization using deep learning-based object detection technique Farag, Mohannad Abdul Nasir, Abd Ghafar Alsibai, Mohammed Hayyan TK Electrical engineering. Electronics Nuclear engineering This work aims to increase the impact of computer vision on robotic positioning and grasping in industrial assembly lines. Real-time object detection and localization problem is addressed for robotic grasp-and-place operation using Selective Compliant Assembly Robot Arm (SCARA). The movement of SCARA robot is guided by deep learning-based object detection for grasp task and edge detection-based position measurement for place task. Deep Convolutional Neural Network (CNN) model, called KSSnet, is developed for object detection based on CNN Alexnet using transfer learning approach. SCARA training dataset with 4000 images of two object categories associated with 20 different positions is created and labeled to train KSSnet model. The position of the detected object is included in prediction result at the output classification layer. This method achieved the state-of-the-art results at 100% precision of object detection, 100% accuracy for robotic positioning and 100% successful real-time robotic grasping within 0.38 seconds as detection time. A combination of Zerocross and Canny edge detectors is implemented on a circular object to simplify the place task. For accurate position measurement, the distortion of camera lens is removed using camera calibration technique where the measured position represents the desired location to place the grasped object. The result showed that the robot successfully moved to the measured position with positioning Root Mean Square Error (0.361, 0.184) mm and 100% for successful place detection. IEEE 2019 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/25004/7/Real-Time%20Robotic%20Grasping%20and%20Localization1.pdf Farag, Mohannad and Abdul Nasir, Abd Ghafar and Alsibai, Mohammed Hayyan (2019) Real-time robotic grasping and localization using deep learning-based object detection technique. In: IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS), 29 June 2019 , Shah Alam, Selangor, Malaysia. pp. 139-144.. ISBN 978-1-7281-0784-4 https://doi.org/10.1109/I2CACIS.2019.8825093
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Malaysia Pahang
building	UMP Institutional Repository
collection	Online Access
language	English
topic	TK Electrical engineering. Electronics Nuclear engineering
spellingShingle	TK Electrical engineering. Electronics Nuclear engineering Farag, Mohannad Abdul Nasir, Abd Ghafar Alsibai, Mohammed Hayyan Real-time robotic grasping and localization using deep learning-based object detection technique
description	This work aims to increase the impact of computer vision on robotic positioning and grasping in industrial assembly lines. Real-time object detection and localization problem is addressed for robotic grasp-and-place operation using Selective Compliant Assembly Robot Arm (SCARA). The movement of SCARA robot is guided by deep learning-based object detection for grasp task and edge detection-based position measurement for place task. Deep Convolutional Neural Network (CNN) model, called KSSnet, is developed for object detection based on CNN Alexnet using transfer learning approach. SCARA training dataset with 4000 images of two object categories associated with 20 different positions is created and labeled to train KSSnet model. The position of the detected object is included in prediction result at the output classification layer. This method achieved the state-of-the-art results at 100% precision of object detection, 100% accuracy for robotic positioning and 100% successful real-time robotic grasping within 0.38 seconds as detection time. A combination of Zerocross and Canny edge detectors is implemented on a circular object to simplify the place task. For accurate position measurement, the distortion of camera lens is removed using camera calibration technique where the measured position represents the desired location to place the grasped object. The result showed that the robot successfully moved to the measured position with positioning Root Mean Square Error (0.361, 0.184) mm and 100% for successful place detection.
format	Conference or Workshop Item
author	Farag, Mohannad Abdul Nasir, Abd Ghafar Alsibai, Mohammed Hayyan
author_facet	Farag, Mohannad Abdul Nasir, Abd Ghafar Alsibai, Mohammed Hayyan
author_sort	Farag, Mohannad
title	Real-time robotic grasping and localization using deep learning-based object detection technique
title_short	Real-time robotic grasping and localization using deep learning-based object detection technique
title_full	Real-time robotic grasping and localization using deep learning-based object detection technique
title_fullStr	Real-time robotic grasping and localization using deep learning-based object detection technique
title_full_unstemmed	Real-time robotic grasping and localization using deep learning-based object detection technique
title_sort	real-time robotic grasping and localization using deep learning-based object detection technique
publisher	IEEE
publishDate	2019
url	http://umpir.ump.edu.my/id/eprint/25004/ http://umpir.ump.edu.my/id/eprint/25004/ http://umpir.ump.edu.my/id/eprint/25004/7/Real-Time%20Robotic%20Grasping%20and%20Localization1.pdf
first_indexed	2023-09-18T22:38:10Z
last_indexed	2023-09-18T22:38:10Z
_version_	1777416735661490176

Real-time robotic grasping and localization using deep learning-based object detection technique

Similar Items