HeteroGenManip: Generalizable Manipulation For Heterogeneous Object Interactions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917483137466368 |
|---|---|
| author | Shen, Zhenhao Yang, Zeming Chen, Yue Wang, Yuran Xu, Shengqiang Li, Mingleyang Dong, Hao Wu, Ruihai |
| author_facet | Shen, Zhenhao Yang, Zeming Chen, Yue Wang, Yuran Xu, Shengqiang Li, Mingleyang Dong, Hao Wu, Ruihai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10201 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HeteroGenManip: Generalizable Manipulation For Heterogeneous Object Interactions Shen, Zhenhao Yang, Zeming Chen, Yue Wang, Yuran Xu, Shengqiang Li, Mingleyang Dong, Hao Wu, Ruihai Robotics Artificial Intelligence 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. |
| title | HeteroGenManip: Generalizable Manipulation For Heterogeneous Object Interactions |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2605.10201 |