English

FViT-Grasp: Grasping Objects With Using Fast Vision Transformers

Robotics 2023-11-27 v1 Computer Vision and Pattern Recognition

Abstract

This study addresses the challenge of manipulation, a prominent issue in robotics. We have devised a novel methodology for swiftly and precisely identifying the optimal grasp point for a robot to manipulate an object. Our approach leverages a Fast Vision Transformer (FViT), a type of neural network designed for processing visual data and predicting the most suitable grasp location. Demonstrating state-of-the-art performance in terms of speed while maintaining a high level of accuracy, our method holds promise for potential deployment in real-time robotic grasping applications. We believe that this study provides a baseline for future research in vision-based robotic grasp applications. Its high speed and accuracy bring researchers closer to real-life applications.

Keywords

Cite

@article{arxiv.2311.13986,
  title  = {FViT-Grasp: Grasping Objects With Using Fast Vision Transformers},
  author = {Arda Sarp Yenicesu and Berk Cicek and Ozgur S. Oguz},
  journal= {arXiv preprint arXiv:2311.13986},
  year   = {2023}
}
R2 v1 2026-06-28T13:29:28.602Z