Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.11321 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908632283611136 |
|---|---|
| author | Liu, Ruizhe Zhou, Pei Luo, Qian Sun, Li Cen, Jun Song, Yibing Yang, Yanchao |
| author_facet | Liu, Ruizhe Zhou, Pei Luo, Qian Sun, Li Cen, Jun Song, Yibing Yang, Yanchao |
| contents | Effective generalization in robotic manipulation requires representations that capture invariant patterns of interaction across environments and tasks. We present a self-supervised framework for learning hierarchical manipulation concepts that encode these invariant patterns through cross-modal sensory correlations and multi-level temporal abstractions without requiring human annotation. Our approach combines a cross-modal correlation network that identifies persistent patterns across sensory modalities with a multi-horizon predictor that organizes representations hierarchically across temporal scales. Manipulation concepts learned through this dual structure enable policies to focus on transferable relational patterns while maintaining awareness of both immediate actions and longer-term goals. Empirical evaluation across simulated benchmarks and real-world deployments demonstrates significant performance improvements with our concept-enhanced policies. Analysis reveals that the learned concepts resemble human-interpretable manipulation primitives despite receiving no semantic supervision. This work advances both the understanding of representation learning for manipulation and provides a practical approach to enhancing robotic performance in complex scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_11321 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data Liu, Ruizhe Zhou, Pei Luo, Qian Sun, Li Cen, Jun Song, Yibing Yang, Yanchao Robotics Effective generalization in robotic manipulation requires representations that capture invariant patterns of interaction across environments and tasks. We present a self-supervised framework for learning hierarchical manipulation concepts that encode these invariant patterns through cross-modal sensory correlations and multi-level temporal abstractions without requiring human annotation. Our approach combines a cross-modal correlation network that identifies persistent patterns across sensory modalities with a multi-horizon predictor that organizes representations hierarchically across temporal scales. Manipulation concepts learned through this dual structure enable policies to focus on transferable relational patterns while maintaining awareness of both immediate actions and longer-term goals. Empirical evaluation across simulated benchmarks and real-world deployments demonstrates significant performance improvements with our concept-enhanced policies. Analysis reveals that the learned concepts resemble human-interpretable manipulation primitives despite receiving no semantic supervision. This work advances both the understanding of representation learning for manipulation and provides a practical approach to enhancing robotic performance in complex scenarios. |
| title | HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.11321 |