DemoFunGrasp：基于示范编辑强化学习的通用灵巧功能抓取
DemoFunGrasp: Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning
将功能抓取条件分解为抓取风格与可供性，并用单条示范编辑重构强化学习问题，为视觉驱动的机器人操作提供样本高效的多任务学习范式；结合视觉语言模型进行规划，实现指令跟随的自主抓取。
原文依据 we leverage a single grasping demonstration and reformulate the RL problem as one-step demonstration editing
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论强化学习（RL）在灵巧抓取中取得了巨大成功，显著提升了抓取性能以及从仿真到真实世界的泛化能力。然而，对下游操作任务至关重要的细粒度功能抓取仍未被充分探索，并面临若干挑战：为跨多样物体的功能抓取指定目标和奖励函数的复杂性、多任务强化学习探索的困难以及仿真到现实迁移的挑战。在本工作中，我们提出DemoFunGrasp用于通用灵巧功能抓取。我们将功能抓取条件分解为两个互补组件——抓取风格和可供性——并将它们集成到一个强化学习框架中，该框架能够学习以任意功能抓取条件抓取任意物体。为解决多任务优化挑战，我们利用单个抓取示范，并将强化学习问题重新表述为一步示范编辑，从而大幅提升样本效率和性能。仿真和真实世界的实验结果表明，DemoFunGrasp能够泛化到未见过的物体、可供性和抓取风格的组合，在成功率和功能抓取准确率上均优于基线。除了强大的仿真到现实能力外，通过结合视觉语言模型（VLM）进行规划，我们的系统实现了自主的指令跟随抓取执行。
英文原文摘要 1461 字符
Reinforcement learning (RL) has achieved great success in dexterous grasping, significantly improving grasp performance and generalization from simulation to the real world. However, fine-grained functional grasping, which is essential for downstream manipulation tasks, remains underexplored and faces several challenges: the complexity of specifying goals and reward functions for functional grasps across diverse objects, the difficulty of multi-task RL exploration, and the challenge of sim-to-real transfer. In this work, we propose DemoFunGrasp for universal dexterous functional grasping. We factorize functional grasping conditions into two complementary components -- grasping style and affordance -- and integrate them into an RL framework that can learn to grasp any object with any functional grasping condition. To address the multi-task optimization challenge, we leverage a single grasping demonstration and reformulate the RL problem as one-step demonstration editing, substantially enhancing sample efficiency and performance.Experimental results in both simulation and the real world show that DemoFunGrasp generalizes to unseen combinations of objects, affordances, and grasping styles, outperforming baselines in both success rate and functional grasping accuracy. In addition to strong sim-to-real capability, by incorporating a vision-language model (VLM) for planning, our system achieves autonomous instruction-following grasp execution.