让机器人通过学习物体可抓取性自动调整姿态，无需预设目标位置。
Grasp-Oriented Non-Prehensile Manipulation via Learning a Graspability Field
- 用可抓取场定义物体姿态的抓取可行性，替代固定目标点。
- 在仿真和真实机器人上成功将物体重定位至可抓取状态。
- 适合需要自主重定位的抓取任务，尤其适用于未知目标姿态场景。
非握持操作常用于机器人抓取前的准备阶段，但现有方法通常依赖预设的目标物体位姿。实际上，物体存在多种可抓取配置，且目标姿态事先未知。本文将非握持操作重新建模为优化以物体为中心的可抓取性目标，而非达到特定位姿。通过合成抓取构建可抓取集，并定义可抓取场来量化不同物体配置对成功抓取的适配程度。该标量度量为强化学习提供密集学习信号，并决定何时终止操纵。由此实现由单一策略驱动的闭环抓取-操纵流水线。仿真与真实机器人实验表明，该策略能可靠地将物体重定位至可抓取状态，并在无需外部规划器或人工设定停止条件的情况下过渡到抓取。预测的可抓取距离与真实抓取成功率高度相关，表明学习到的表示有效捕捉了物体配置的抓取可行性。
原文摘要 · Abstract (English)
Non-prehensile manipulation is often used as a preparatory step for robotic grasping, yet existing approaches typically require a predefined target object pose. In practice, however, objects admit multiple graspable configurations and the desired pose is not known in advance. We reformulate non-prehensile manipulation for grasping as optimizing an object centric graspability objective rather than reaching a specific pose. We construct a graspable set from synthesized grasps and define a graspability field that measures how suitable an object configuration is for successful grasp execution. The scalar measure provides a dense learning signal for reinforcement learning and determines when to terminate manipulation. This yields a closed-loop manipulation-to-grasp pipeline driven by a single policy. Experiments in simulation and on a real robot show that the policy reliably reconfigures objects into graspable states and transitions to grasping without external planners or manually specified stopping conditions. The predicted graspability distance correlates with real world grasp success, which indicates that the learned representation captures grasp feasibility of object configurations.
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。