用强化学习让机械手通过环境互动抓取大件无法抓取的物体。
Dexterous Non-Prehensile Manipulation for Ungraspable Object via Extrinsic Dexterity
- 通过强化学习训练两种操作策略：推到边缘或墙边
- 在数十种家用物品上验证，新物体也能泛化成功
- 仿真学的策略直接用于真实机器人，无需再训练
当物体底面积过大超出末端执行器最大开合范围时，便无法被传统抓取。现有方法借助环境特征实现非抓握式操控（extrinsic dexterity）。虽然夹持器已在此领域取得一定成效，但灵巧手具有更强灵活性和交互能力，控制难度更高。本文提出ExDex系统，基于强化学习实现灵巧手对不可抓取物体的非抓握式操控。该系统学习两种策略：将物体从桌面中央移至边缘以直接抓取，或移至墙面，利用环境互动完成抓取。我们在数十种不同家用物体上进行了大量实验，验证了方法在性能与泛化能力上的优越性。此外，所学策略可直接从仿真迁移到真实机器人系统，无需额外训练，充分证明其在真实场景中的适用性。项目网站：https://tangty11.github.io/ExDex/
原文摘要 · Abstract (English)
Objects with large base areas become ungraspable when they exceed the end-effector's maximum aperture. Existing approaches address this limitation through extrinsic dexterity, which exploits environmental features for non-prehensile manipulation. While grippers have shown some success in this domain, dexterous hands offer superior flexibility and manipulation capabilities that enable richer environmental interactions, though they present greater control challenges. Here we present ExDex, a dexterous arm-hand system that leverages reinforcement learning to enable non-prehensile manipulation for grasping ungraspable objects. Our system learns two strategic manipulation sequences: relocating objects from table centers to edges for direct grasping, or to walls where extrinsic dexterity enables grasping through environmental interaction. We validate our approach through extensive experiments with dozens of diverse household objects, demonstrating both superior performance and generalization capabilities with novel objects. Furthermore, we successfully transfer the learned policies from simulation to a real-world robot system without additional training, further demonstrating its applicability in real-world scenarios. Project website: https://tangty11.github.io/ExDex/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。