.png){kind=icon}
.png){kind=icon}
Return
MetaGrasp: Generalizable Dexterous Multifingered Functional Grasping With Gradual Skill Curriculum Learning
.png){kind=icon}
PRE
AI
Y
Q
X
J
W
孙
DOI：10.1109/tnnls.2026.3655749.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Dexterous grasping and manipulation with multifingered robotic hands presents a significant challenge due to their high degrees of freedom and the need for task-specific adaptations. Existing methods usually adopt single-task learning framework or focus on simple stable wrap grasping, limiting their efficiency and generalization ability when encountering new task or precise functional grasping pose. In this article, we introduce <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MetaGrasp</b>, a novel approach that defines dexterous functional grasping as a multitask reinforcement learning (RL) problem based on hand grasp pose classification. Our method features a unique gradual skill curriculum learning (GSCL) framework, which structures the learning process into three stages: <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">beginner</b>, <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">intermediate</b>, and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">advanced</b> curriculum learning according to the level of difficulty. <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MetaGrasp</b> leverages this hierarchical learning structure to develop a versatile, adaptive grasping policy that can grasp objects based on hand grasp pose and object point cloud inputs. Taking five hand grasp types as research cases, the trained policy with our <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MetaGrasp</b> can be easily adpated to grasp different object instances from different object categories according to functional grasp intentions specified by one expert demonstration without requiring extensive system interaction. We categorize the dexterous functional grasping tasks of a five-fingered robotic hand into multiple tasks based on hand poses for RL, and to combine meta imitation learning (IL) with curriculum learning. The experimental results show that the <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MetaGrasp</b> has better one-shot generalization ability on new grasp tasks, and outperforms state-of-the-art single-task dexterous grasping methods.
Keywords:
Curriculum learning
dexterous functional grasp
imitation learning (IL)
multitask
one-shot IL (OSIL)
reinforcement learning (RL)
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W
Organization
Cited Papers