Enhanced Robotic Grasp Detection through Advanced Resnet Variants in Deep Convolutional Neural Networks

Tanya Thukral

doi:10.36948/ijfmr.2024.v06i04.21289

Enhanced Robotic Grasp Detection through Advanced Resnet Variants in Deep Convolutional Neural Networks

Author(s)	Tanya Thukral
Country	India
Abstract	The advent of deep learning has propelled significant advancements in the field of robotic manipulation, enabling robots to perform complex grasping tasks with unprecedented accuracy. This study introduces an innovative approach to robotic grasp detection leveraging advanced variants of the Residual Network (ResNet) architecture within Deep Convolutional Neural Networks (DCNNs). Our methodology extends the conventional ResNet framework by integrating novel structural modifications and optimization techniques aimed at enhancing feature representation and learning efficiency. By incorporating dilated convolutions, attention mechanisms, and depth-wise separable convolutions, our proposed ResNet variants significantly improve the grasp detection performance in terms of accuracy, speed, and robustness across diverse object categories and orientations. The effectiveness of our approach is validated through extensive experiments on standard robotic grasp datasets, where our models demonstrate superior performance compared to existing state-of-the-art grasp detection methodologies. Furthermore, our analysis reveals that the advanced ResNet variants are capable of learning more discriminative features from grasp imagery, facilitating more precise localization and orientation prediction for robotic grippers. Additionally, the computational efficiency of our models enables real-time grasp detection, which is critical for practical robotic applications. Advanced techniques in deep learning have signiﬁcantly propelled the ﬁelds of computer vision and natural language processing forward. Despite notable achievements, the integration of deep learning into robotics applications remains relatively limited. This study introduces a novel approach to robotic grasp detection, focusing on predicting the optimal grasping pose for a parallel-plate robotic gripper when encountering unfamiliar objects, utilizing RGB-D imagery of the scene.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 6, Issue 4, July-August 2024
Published On	2024-07-18
Cite This	Enhanced Robotic Grasp Detection through Advanced Resnet Variants in Deep Convolutional Neural Networks - Tanya Thukral - IJFMR Volume 6, Issue 4, July-August 2024. DOI 10.36948/ijfmr.2024.v06i04.21289
DOI	https://doi.org/10.36948/ijfmr.2024.v06i04.21289
Short DOI	https://doi.org/gt43xj

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 6 Isu 4 Cover Page Vol 6 Isu 3 Cover Page Vol 6 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-5948-55	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Enhanced Robotic Grasp Detection through Advanced Resnet Variants in Deep Convolutional Neural Networks

Share this