GraspLDP：通过潜变量扩散实现可泛化的抓取策略
GraspLDP: Towards Generalizable Grasping Policy via Latent Diffusion
把抓取位姿先验与抓取性（graspness）自监督重建目标注入潜扩散策略的反向去噪过程，可作为在视觉-动作策略中嵌入几何/任务先验的通用手段，对做机器人操作与视觉-动作联合建模的研究者可直接复用。
原文依据 we employ a latent diffusion policy to guide action chunk decoding with grasp pose prior
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文关注提升通过模仿学习得到的操作策略的抓取精度与泛化能力。基于扩散的策略学习方法近来已成为机器人操作任务的主流方案。由于抓取是操作中的关键子任务，模仿学习策略能否执行精确且可泛化的抓取尤其值得关注。现有的抓取模仿学习技术常常存在抓取执行不精确、空间泛化受限以及物体泛化能力差的问题。为应对这些挑战，我们将抓取先验知识引入扩散策略框架。具体而言，我们采用潜变量扩散策略，以抓取位姿先验引导动作块解码，确保生成的运动轨迹紧密贴合可行的抓取构型。此外，我们在扩散过程中引入自监督重建目标以嵌入抓取性先验：在每一个反向扩散步，我们从中间表示反投影出抓取性并重建腕部相机图像。仿真与真实机器人实验均表明，我们的方法显著优于基线方法，并展现出较强的动态抓取能力。
英文原文摘要 1294 字符
This paper focuses on enhancing the grasping precision and generalization of manipulation policies learned via imitation learning. Diffusion-based policy learning methods have recently become the mainstream approach for robotic manipulation tasks. As grasping is a critical subtask in manipulation, the ability of imitation-learned policies to execute precise and generalizable grasps merits particular attention. Existing imitation learning techniques for grasping often suffer from imprecise grasp executions, limited spatial generalization, and poor object generalization. To address these challenges, we incorporate grasp prior knowledge into the diffusion policy framework. In particular, we employ a latent diffusion policy to guide action chunk decoding with grasp pose prior, ensuring that generated motion trajectories adhere closely to feasible grasp configurations. Furthermore, we introduce a self-supervised reconstruction objective during diffusion to embed the graspness prior: at each reverse diffusion step, we reconstruct wrist-camera images back-projected the graspness from the intermediate representations. Both simulation and real robot experiments demonstrate that our approach significantly outperforms baseline methods and exhibits strong dynamic grasping capabilities.