Learning Form Closure Grasping with a Four-Pin Parallel Gripper
Open Access
- 15 February 2023
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 13 (4) , 2506
Abstract
Being able to stably grasp with generalization is one of the distinguished capabilities for building a generic grasping system for robots. In this work, we propose a stable grasping method for four-pin parallel grippers within a reinforcement learning framework. First, a reinforcement learning problem is constructed on the basis of the improved four-pin gripper. Then, the learning policy and the reward function are constructed in consideration of the knowledge of environmental constraint and form closure. Finally, the effectiveness of the designed grasping method is validated in a simulated environment, and the results demonstrate that a safe and stable grasp can be planned for given 2.5D objects.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFE0107300, 62003059, 2020B0909020001, 2020M673136, XmT2020123)
- National Natural Science Foundation of China (2022YFE0107300, 62003059, 2020B0909020001, 2020M673136, XmT2020123)
- Key-Area Research and Development Program of Guangdong Province (2022YFE0107300, 62003059, 2020B0909020001, 2020M673136, XmT2020123)
- China Postdoctoral Science Foundation (2022YFE0107300, 62003059, 2020B0909020001, 2020M673136, XmT2020123)
- Chongqing Postdoctoral Research Project Special Grant (2022YFE0107300, 62003059, 2020B0909020001, 2020M673136, XmT2020123)
This publication has 23 references indexed in Scilit:
- Yale OpenHand Project: Optimizing Open-Source Hand Designs for Ease of Fabrication and AdoptionIEEE Robotics & Automation Magazine, 2017
- A data-driven statistical framework for post-grasp manipulationThe International Journal of Robotics Research, 2014
- Modelling and Control of the Barrett Hand for Grasping2013
- Learning hardware agnostic grasps for a universal jamming gripper2012
- Efficient grasping from RGBD images: Learning using a new rectangle representation2011
- Multisensory five-finger dexterous hand: The DLR/HIT Hand II2008
- Analysis of Stable Grasping for One-Parameter Four-Pin Gripper2008
- A Quantitative Test For Form Closure Grasps2005
- Distributed form closure for convex planar objects through reinforcement learning with local information2005
- The Shadow robot mimics human actionsIndustrial Robot: the international journal of robotics research and application, 2003