International Journal of Mechanical and Production Engineering (IJMPE)
.
Follow Us On :
current issues
Volume-12,Issue-7  ( Jul, 2024 )
Past issues
  1. Volume-12,Issue-6  ( Jun, 2024 )
  2. Volume-12,Issue-5  ( May, 2024 )
  3. Volume-12,Issue-4  ( Apr, 2024 )
  4. Volume-12,Issue-3  ( Mar, 2024 )
  5. Volume-12,Issue-2  ( Feb, 2024 )
  6. Volume-12,Issue-1  ( Jan, 2024 )
  7. Volume-11,Issue-12  ( Dec, 2023 )
  8. Volume-11,Issue-11  ( Nov, 2023 )
  9. Volume-11,Issue-10  ( Oct, 2023 )
  10. Volume-11,Issue-9  ( Sep, 2023 )

Statistics report
Nov. 2024
Submitted Papers : 80
Accepted Papers : 10
Rejected Papers : 70
Acc. Perc : 12%
Issue Published : 136
Paper Published : 2427
No. of Authors : 6944
  Journal Paper


Paper Title :
Learning Pushing and Grasping Via Deep Reinforcement Learning and Grasping Potential Module

Author :Yu-Hsiangshao, Chih-Yung Huang, Ying-Chun Wang

Article Citation :Yu-Hsiangshao ,Chih-Yung Huang ,Ying-Chun Wang , (2024 ) " Learning Pushing and Grasping Via Deep Reinforcement Learning and Grasping Potential Module " , International Journal of Mechanical and Production Engineering (IJMPE) , pp. 1-7, Volume-12,Issue-4

Abstract : Robotic arms are often used for grasping objects, but grasping in cluttered scenarios may lead to collisions due to insufficient space. Pushing can help scatter cluttered objects to make space for robotic arm hence increasing the grasp success rate. In this paper, we propose a method that combines deep reinforcement learning with instance segmentation networks to achieve collaborative pushing and grasping. In our work, we use a grasping potential module to estimate the grasp potential of different objects in the environment.The agent prioritizes grasping high-potential objects, allowing it to quickly learn the pushing and grasping policies in complex environments. Additionally, a novel pushing strategy is proposed to prevent ineffective pushing. Experimental results validate that our method achieves a 93% grasp success rate and converges faster than other baseline models. Keywords - Deep Reinforcement Learning, Instance Segmentation, Grasping

Type : Research paper

Published : Volume-12,Issue-4


DOIONLINE NO - IJMPE-IRAJ-DOIONLINE-20720   View Here

Copyright: © Institute of Research and Journals

| PDF |
Viewed - 46
| Published on 2024-07-11
   
   
IRAJ Other Journals
IJMPE updates
Volume-12,Issue-7 (July, 2024 )
The Conference World

JOURNAL SUPPORTED BY