arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.22862cs.ROcs.CV
收藏

GraspLDP: 通过潜在扩散实现通用抓取策略

GraspLDP: Towards Generalizable Grasping Policy via Latent Diffusion

State Key Laboratory of Complex and Critical Software Environment(复杂与关键软件环境国家重点实验室);School of Computer Science and Engineering(计算机科学与工程学院)

Enda Xiang, Haoxiang Ma, Xinzhu Ma, Zicheng Liu, Di Huang

AI总结:

GraspLDP通过引入潜在扩散框架和抓取先验知识,提升了抓取策略的精度和泛化能力,实验表明其在动态抓取任务中表现优异。

摘要:

本文聚焦于通过模仿学习提升操纵策略的抓取精度和泛化能力。基于扩散的策略学习方法最近已成为机器人操纵任务的主流方法。由于抓取是操纵任务中的关键子任务,模仿学习策略执行精确且可泛化的抓取能力值得特别关注。现有的抓取模仿学习技术往往存在抓取执行不精确、空间泛化能力有限和物体泛化能力差的问题。为了解决这些挑战,我们将在扩散策略框架中引入抓取先验知识。具体而言,我们采用潜在扩散策略,利用抓取姿态先验知识指导动作块解码,确保生成的运动轨迹紧密贴合可行的抓取配置。此外,我们引入了自监督重建目标进行扩散,以嵌入抓取先验:在每次反向扩散步骤中,我们从中间表示中重建腕部相机图像的投影抓取信息。仿真和真实机器人实验表明,我们的方法显著优于基线方法,并表现出强大的动态抓取能力。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑