论文/arXiv 2610.21735·13 天前

Uni-PNP：面向可泛化物体位姿到达的统一抓取与非抓取策略学习

Uni-PNP通过接触动力学几何编码器与两阶段强化学习，统一学习抓取/非抓取操作，并在多物体多夹爪位姿到达中验证。

AI 整理

• 数据与采集
• 具身模型
• 端侧部署

原文链接：Uni-PNP: Unified Prehensile and Non-prehensile Policy Learning for Generalizable Object Pose Reaching（arXiv 2610.21735 · 发布日期：2026-10-15）

Uni-PNP: Unified Prehensile and Non-prehensile Policy Learning for Generalizable Object Pose Reaching

Uni-PNP通过接触动力学几何编码器与两阶段强化学习，统一学习抓取/非抓取操作，并在多物体多夹爪位姿到达中验证。

核心要点

• 现有方法常分开开发抓取与非抓取能力，依赖中间目标串接，限制接触运动与抓取协同。
• 方法先预训练几何编码器预测接触导致的物体运动，再用两阶段强化学习课程训练统一策略。
• 实验在数百个已见物体上成功率76.39%，未见同类为57.91%，分别超过最强基线20.52和17.79个百分点。
• 分析了非抓取/抓取重定位、倾倒后抓取、抓取中借助桌面重定向等涌现行为，并提供项目页。

验证范围与局限：验证范围包括多样物体与夹爪的仿真交互、数百个已见/未见物体实验，并展示到真实场景的迁移。

英文摘要 (Abstract)

Object manipulation often requires combining non-prehensile actions with grasping. However, existing approaches typically develop these capabilities separately and integrate them by sequencing distinct primitives through prescribed intermediate objectives, limiting the coordination of contact motions and grasping. Their integration also remains sensitive to object and gripper geometry and depends on particular environmental supports, complicating real-world deployment. We present Uni-PNP, a unified policy that jointly learns prehensile and non-prehensile manipulation for object pose reaching across diverse objects and grippers. To achieve this, we first pretrain a geometry encoder to predict contact-induced object motion using a contact-dynamics dataset constructed from simulated interactions between diverse objects and grippers. We then train the policy in a two-stage reinforcement learning curriculum from graspable objects to ungraspable peers, encouraging the discovery of non-prehensile interactions and their integration with grasping. Experiments show 76.39% success on hundreds of seen objects with grippers, and 57.91% on unseen peers, outperforming the strongest pose-reaching baseline by 20.52 and 17.79 percentage points, respectively. We also analyze emergent behaviors, including nonprehensile and prehensile repositioning, grasp acquisition that requires grasping after tipping, and table-assisted reorientation while grasping, and transfer to the real-world scenario. Project page available at lgswdn.github.io/Uni-PNP.

作者：Wenxuan Zhu, Yuze Wang, Jiangran Lyu, Jiayi Chen, Yixin Zheng, Mi Yan, Li Yi, Zhizheng Zhang, He Wang

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.21735：Uni-PNP: Unified Prehensile and Non-prehensile Policy Learning for Generalizable Object Pose Reaching访问 2026-10-21