0% Complete
صفحه اصلی
/
سی و سومین کنفرانس بین المللی مهندسی برق
SGG-Net: Skeleton and Graph-Based Neural Network Approaches for Grasping Objects
نویسندگان :
AliReza Beigy
1
Farbod Azimmohseni
2
Ali Sabzejou
3
Mehdi Tale Masouleh
4
Ahmad Kalhor
5
1- دانشگاه تهران
2- دانشگاه تهران
3- دانشگاه تهران
4- دانشگاه تهران
5- دانشگاه تهران
کلمات کلیدی :
Robotic،Grasping،Grasp Pose Estimation،Graph Neural Networks،Straight Skeleton
چکیده :
Efficient and robust robotic grasping in cluttered, unstructured environments remains a critical challenge. Existing 6-DoF grasping techniques frequently rely on processing the entire observed point cloud, which can lead to high computational overhead and reduced precision. This paper introduces Skeleton and Graph-based Grasping Network (SGG-Net), an integrated framework that combines geometric skeletonization, implemented through the 3D-StSkel algorithm, with a Graph Neural Network (GNN) to effectively identify optimal grasp poses for robotic manipulation. The proposed method significantly narrows the search space by extracting and focusing on geometrically salient regions, enabling faster and more reliable 6-DoF grasp pose generation. Experimental evaluations demonstrate the approach’s strong performance across benchmark datasets, achieving grasp success rates of 90.74% on DexNet, 81.63% on EGAD, and 97.30% on YCB objects. Furthermore, the method outperformed state-of-the-art approaches on the GraspNet-1Billion dataset, achieving the highest Average Precision (AP) scores for both seen and novel objects. Experimental evaluations on multiple benchmark datasets, including DexNet, EGAD, YCB, and GraspNet-1Billion, show that the proposed technique achieves state-of-the-art grasp success rates and generalizes effectively to diverse and complex object shapes. This approach thus provides a scalable, accurate, and computationally efficient solution for grasp estimation, advancing robotic manipulation capabilities in real-world scenarios.
لیست مقالات
لیست مقالات بایگانی شده
Social Welfare Maximization with Demand Response Program Using Stackelberg Game Theory
Mahtab Seyyedi - Ebrahim Pirmoradi - Turaj Amraee
An event-triggered distributed consensus information filter for target tracking in sensor networks
Sara Giyani - Behrouz Safarinejadian - Sajad Shamsi
Exploring Graph Biomarkers and Connectivity in Epilepsy Through Graph Learning
Ali Khosravipour - Sepideh Hajipour Sardouie
On spatiotemporal-aware deep neural networks for real-time video fire detection: empowering image-based models with temporal and spatial features of video
Mahdi Shamisavi - Sahar Eslami - Amir Jahanshahi - Morteza Rajabzadeh
Robot-Assisted Rehabilitation with Optimal Impedance: Using an $\mathcal{EKF}$-Based $\mathcal{L}asso-\mathcal{MPC}$
Hossein Ahmadian - Iman Sharifi - Heidar Ali Talebi
Phase-Only Array Antenna Beamforming with Minimum Peak Sidelobe Level and Minimum Power Loss Criteria
Mahdi Hatam
Devloping a clustering routing algorithm based on the efficient hybrid methodology for WSN performance optimization
Neda Mazloomi - Sajad Haghzad Klidbary
Effect of Passivation on the Structural and Electronic Properties of Armchair MoSe2 Nanoribbons: A First-Principles Investigation
ََAmirreza Ghazi - Arash Yazdanpanah
An Open-Loop Time Amplifier With Zero-Gain Delay in Output for Coarse-Fine Time to Digital Converters
Seyyed Morteza Golzan - Jafar Sobhi - Ziaddin Daie Koozehkanani
Stray Load Losses Determination Methods of Induction Motors-A Review
Moslem Geravandi - Hassan Moradi CheshmehBeigi
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.3