DexFormer 2.0: Towards a Cross-Embodiment Foundation Policy for Dexterous Grasping
暂无中文版,显示英文原文。
摘自论文摘要
Dexterous grasping policies are usually trained for one arm paired with one hand. Every new pairing then needs its own policy, and the number of policies grows with every arm and hand added.
摘自论文摘要,摘要生成中。