ODGNet: Robotic Grasp Detection Network Based on Omni-Dimensional Dynamic Convolution

Author:

Kuang Xinghong1,Tao Bangsheng1

Affiliation:

1. School of Engineering, Shanghai Ocean University, No. 999 Hucheng Ring Road, Shanghai 201306, China

Abstract

In this article, to further improve the accuracy and speed of grasp detection for unknown objects, a new omni-dimensional dynamic convolution grasp detection network (ODGNet) is proposed. The ODGNet includes two key designs. Firstly, it integrates omni-dimensional dynamic convolution to enhance the feature extraction of the graspable region. Secondly, it employs a grasping region feature enhancement fusion module to refine the features of the graspable region and promote the separation of the graspable region from the background. The ODGNet attained an accuracy of 98.4% and 97.8% on the image-wise and object-wise subsets of the Cornell dataset, respectively. Moreover, the ODGNet’s detection speed can reach 50 fps. A comparison with previous algorithms shows that the ODGNet not only improves the grasp detection accuracy, but also satisfies the requirement of real-time grasping. The grasping experiments in the simulation environment verify the effectiveness of the proposed algorithm.

Funder

National Key Research and Development Program of China: Design and Development of High Performance Marine Electric Field Sensor

Publisher

MDPI AG

Reference38 articles.

1. Vision-Based Robotic Grasping from Object Localization, Object Pose Estimation to Grasp Estimation for Parallel Grippers: A Review;Du;Artif. Intell. Rev.,2021

2. A Review of Robotic Grasp Detection Technology;Dong;Robotica,2023

3. Jiang, Y., Moseson, S., and Saxena, A. (2011, January 9–13). Efficient Grasping from RGBD Images: Learning Using a New Rectangle Representation. Proceedings of the 2011 IEEE International Conference on Robotics and Automation, Shanghai, China.

4. Deep Learning for Detecting Robotic Grasps;Lenz;Int. J. Robot. Res.,2015

5. Redmon, J., and Angelova, A. (2015, January 26–30). Real-Time Grasp Detection Using Convolutional Neural Networks. Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), Washington, DC, USA.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3