MetaGrasp: Generalizable Dexterous Multifingered Functional Grasping With Gradual Skill Curriculum Learning
- 6 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP (2162237X) , 1-15
Abstract
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 MetaGrasp, 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: beginner, intermediate, and advanced curriculum learning according to the level of difficulty. MetaGrasp 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 MetaGrasp 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 MetaGrasp has better one-shot generalization ability on new grasp tasks, and outperforms state-of-the-art single-task dexterous grasping methods.Keywords
Funding Information
- National Natural Science Foundation of China (62373075)
- National Natural Science Foundation of China (61873046)
This publication has 28 references indexed in Scilit:
- UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping2025
- GraspXL: Generating Grasping Motions for Diverse Objects at Scale2024
- HOLD: Category-Agnostic 3D Reconstruction of Interacting Hands and Objects from Video2024
- UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning2023
- UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy2023
- ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging2019
- Classifying human manipulation behavior2011
- Multitask LearningMachine Learning, 1997
- Reinforcement learning in continuous time: advantage updating1994
- On grasp choice, grasp models, and the design of hands for manufacturing tasksIEEE Transactions on Robotics and Automation, 1989