Cargando…

Pixel-Reasoning-Based Robotics Fine Grasping for Novel Objects with Deep EDINet Structure

Robotics grasp detection has mostly used the extraction of candidate grasping rectangles; those discrete sampling methods are time-consuming and may ignore the potential best grasp synthesis. This paper proposes a new pixel-level grasping detection method on RGB-D images. Firstly, a fine grasping re...

Descripción completa

Detalles Bibliográficos
Autores principales: Shi, Chaoquan, Miao, Chunxiao, Zhong, Xungao, Zhong, Xunyu, Hu, Huosheng, Liu, Qiang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9185561/
https://www.ncbi.nlm.nih.gov/pubmed/35684904
http://dx.doi.org/10.3390/s22114283
_version_ 1784724751308029952
author Shi, Chaoquan
Miao, Chunxiao
Zhong, Xungao
Zhong, Xunyu
Hu, Huosheng
Liu, Qiang
author_facet Shi, Chaoquan
Miao, Chunxiao
Zhong, Xungao
Zhong, Xunyu
Hu, Huosheng
Liu, Qiang
author_sort Shi, Chaoquan
collection PubMed
description Robotics grasp detection has mostly used the extraction of candidate grasping rectangles; those discrete sampling methods are time-consuming and may ignore the potential best grasp synthesis. This paper proposes a new pixel-level grasping detection method on RGB-D images. Firstly, a fine grasping representation is introduced to generate the gripper configurations of parallel-jaw, which can effectively resolve the gripper approaching conflicts and improve the applicability to unknown objects in cluttered scenarios. Besides, the adaptive grasping width is used to adaptively represent the grasping attribute, which is fine for objects. Then, the encoder–decoder–inception convolution neural network (EDINet) is proposed to predict the fine grasping configuration. In our findings, EDINet uses encoder, decoder, and inception modules to improve the speed and robustness of pixel-level grasping detection. The proposed EDINet structure was evaluated on the Cornell and Jacquard dataset; our method achieves 98.9% and 96.1% test accuracy, respectively. Finally, we carried out the grasping experiment on the unknown objects, and the results show that the average success rate of our network model is 97.2% in a single object scene and 93.7% in a cluttered scene, which out-performs the state-of-the-art algorithms. In addition, EDINet completes a grasp detection pipeline within only 25 ms.
format Online
Article
Text
id pubmed-9185561
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91855612022-06-11 Pixel-Reasoning-Based Robotics Fine Grasping for Novel Objects with Deep EDINet Structure Shi, Chaoquan Miao, Chunxiao Zhong, Xungao Zhong, Xunyu Hu, Huosheng Liu, Qiang Sensors (Basel) Article Robotics grasp detection has mostly used the extraction of candidate grasping rectangles; those discrete sampling methods are time-consuming and may ignore the potential best grasp synthesis. This paper proposes a new pixel-level grasping detection method on RGB-D images. Firstly, a fine grasping representation is introduced to generate the gripper configurations of parallel-jaw, which can effectively resolve the gripper approaching conflicts and improve the applicability to unknown objects in cluttered scenarios. Besides, the adaptive grasping width is used to adaptively represent the grasping attribute, which is fine for objects. Then, the encoder–decoder–inception convolution neural network (EDINet) is proposed to predict the fine grasping configuration. In our findings, EDINet uses encoder, decoder, and inception modules to improve the speed and robustness of pixel-level grasping detection. The proposed EDINet structure was evaluated on the Cornell and Jacquard dataset; our method achieves 98.9% and 96.1% test accuracy, respectively. Finally, we carried out the grasping experiment on the unknown objects, and the results show that the average success rate of our network model is 97.2% in a single object scene and 93.7% in a cluttered scene, which out-performs the state-of-the-art algorithms. In addition, EDINet completes a grasp detection pipeline within only 25 ms. MDPI 2022-06-04 /pmc/articles/PMC9185561/ /pubmed/35684904 http://dx.doi.org/10.3390/s22114283 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Shi, Chaoquan
Miao, Chunxiao
Zhong, Xungao
Zhong, Xunyu
Hu, Huosheng
Liu, Qiang
Pixel-Reasoning-Based Robotics Fine Grasping for Novel Objects with Deep EDINet Structure
title Pixel-Reasoning-Based Robotics Fine Grasping for Novel Objects with Deep EDINet Structure
title_full Pixel-Reasoning-Based Robotics Fine Grasping for Novel Objects with Deep EDINet Structure
title_fullStr Pixel-Reasoning-Based Robotics Fine Grasping for Novel Objects with Deep EDINet Structure
title_full_unstemmed Pixel-Reasoning-Based Robotics Fine Grasping for Novel Objects with Deep EDINet Structure
title_short Pixel-Reasoning-Based Robotics Fine Grasping for Novel Objects with Deep EDINet Structure
title_sort pixel-reasoning-based robotics fine grasping for novel objects with deep edinet structure
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9185561/
https://www.ncbi.nlm.nih.gov/pubmed/35684904
http://dx.doi.org/10.3390/s22114283
work_keys_str_mv AT shichaoquan pixelreasoningbasedroboticsfinegraspingfornovelobjectswithdeepedinetstructure
AT miaochunxiao pixelreasoningbasedroboticsfinegraspingfornovelobjectswithdeepedinetstructure
AT zhongxungao pixelreasoningbasedroboticsfinegraspingfornovelobjectswithdeepedinetstructure
AT zhongxunyu pixelreasoningbasedroboticsfinegraspingfornovelobjectswithdeepedinetstructure
AT huhuosheng pixelreasoningbasedroboticsfinegraspingfornovelobjectswithdeepedinetstructure
AT liuqiang pixelreasoningbasedroboticsfinegraspingfornovelobjectswithdeepedinetstructure