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 2605.10201cs.ROcs.AI
收藏

HeteroGenManip:异构物体交互的通用操作

HeteroGenManip: Generalizable Manipulation For Heterogeneous Object Interactions

Peking University(北京大学);Tianjin University(天津大学)

Zhenhao Shen, Zeming Yang, Yue Chen, Yuran Wang, Shengqiang Xu, Mingleyang Li, Hao Dong, Ruihai Wu

AI总结:

本文提出HeteroGenManip框架,通过两阶段方法解决机器人异构物体交互中的接触点定位和轨迹规划问题,实现跨类型物体的鲁棒泛化。

摘要:

通用化涉及跨类型物体交互的操作是机器人领域关键但具有挑战性的能力。为可靠完成此类任务,机器人必须解决两个根本挑战:'在哪里操作'(接触点定位)和'如何操作'(后续交互轨迹规划)。现有基于基础模型的方法通常采用端到端学习,模糊了这些阶段的区别,加剧了长时间任务中的误差累积。此外,它们通常依赖单一统一模型,无法捕捉异构物体所需的多样化、类别特定特征。为克服这些限制,我们提出HeteroGenManip,一种任务条件的两阶段框架,旨在将初始抓取与复杂交互执行分离。首先,Foundation-Correspondence-Guided Grasp模块利用结构先验对齐初始接触状态,从而显著减少抓取姿态的不确定性。随后,Multi-Foundation-Model Diffusion Policy(MFMDP)将物体路由到类别专用的基础模型,通过双流交叉注意机制整合细粒度几何信息与高度可变的部件特征。实验评估表明,HeteroGenManip在模拟任务中实现平均31%的性能提升,在广泛类型设置中,同时在四个不同交互类型的现实任务中实现36.7%的提升。

英文摘要:

Generalizable manipulation involving cross-type object interactions is a critical yet challenging capability in robotics. To reliably accomplish such tasks, robots must address two fundamental challenges: "where to manipulate" (contact point localization) and "how to manipulate" (subsequent interaction trajectory planning). Existing foundation-model-based approaches often adopt end-to-end learning that obscures the distinction between these stages, exacerbating error accumulation in long-horizon tasks. Furthermore, they typically rely on a single uniform model, which fails to capture the diverse, category-specific features required for heterogeneous objects. To overcome these limitations, we propose HeteroGenManip, a task-conditioned, two-stage framework designed to decouple initial grasp from complex interaction execution. First, Foundation-Correspondence-Guided Grasp module leverages structural priors to align the initial contact state, thereby significantly reducing the pose uncertainty of grasping. Subsequently, Multi-Foundation-Model Diffusion Policy (MFMDP) routes objects to category-specialized foundation models, integrating fine-grained geometric information with highly-variable part features via a dual-stream cross-attention mechanism. Experimental evaluations demonstrate that HeteroGenManip achieves robust intra-category shape and pose generalization. The framework achieves an average 31% performance improvement in simulation tasks with broad type setting, alongside a 36.7% gain across four real-world tasks with different interaction types.

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。

↑