UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning

Wen‐Ming Wan,Haoran Geng,Yun Liu,Zikang Shan, Yanfei Yang, Yang Li,He Wang

arXiv (Cornell University)(2023)

引用 0|浏览0
暂无评分
摘要
We propose a novel, object-agnostic method for learning a universal policy for dexterous object grasping from realistic point cloud observations and proprioceptive information under a table-top setting, namely UniDexGrasp++. To address the challenge of learning the vision-based policy across thousands of object instances, we propose Geometry-aware Curriculum Learning (GeoCurriculum) and Geometry-aware iterative Generalist-Specialist Learning (GiGSL) which leverage the geometry feature of the task and significantly improve the generalizability. With our proposed techniques, our final policy shows universal dexterous grasping on thousands of object instances with 85.4% and 78.2% success rate on the train set and test set which outperforms the state-of-the-art baseline UniDexGrasp by 11.7% and 11.3%, respectively.
更多
查看译文
关键词
dexterous grasping policy learning,curriculum,geometry-aware,generalist-specialist
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要