Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.22082 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917541812633600 |
|---|---|
| author | Wang, Wentian Wen, Chutong Ma, Hongxu Wang, Wuhao Xue, Zhexiong Nizamani, Abdul Haseeb Zhou, Dandi Sun, Xinhai Zhu, Jianqiao |
| author_facet | Wang, Wentian Wen, Chutong Ma, Hongxu Wang, Wuhao Xue, Zhexiong Nizamani, Abdul Haseeb Zhou, Dandi Sun, Xinhai Zhu, Jianqiao |
| contents | We present CoRMA(Contrastive Robotic Motor Adaptation), a context-based meta-adaptation framework that modifies RMA for force-dominant assembly. CoRMA replaces raw simulator-parameter adaptation with a compact 6D simulator-only semantic contact context describing contact onset, lateral engagement, guided transition, contact direction, and jamming. A deployable causal Transformer adapter infers this context online from force, proprioceptive, and action histories using semantic regression and a force-regime contrastive objective. At deployment, oracle context is removed and replaced by the inferred context, enabling within-episode adaptation without demonstrations, privileged inputs, or gradient updates. We evaluate CoRMA on PegInsert, GearMesh, and NutThread in Isaac Lab / Isaac Sim 5.0 and on a real Marvin arm. Compared with FORGE baselines that achieve high simulation success but degrade substantially on hardware, CoRMA retains higher verified real success under controlled target-pose noise. These results support semantic contact inference as a reusable adaptation interface within a related assembly task family, while broader unseen-task generalization and Real2Sim calibration remain future work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22082 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CoRMA: Contrastive RMA for Contact-Rich Meta-Adaptation Wang, Wentian Wen, Chutong Ma, Hongxu Wang, Wuhao Xue, Zhexiong Nizamani, Abdul Haseeb Zhou, Dandi Sun, Xinhai Zhu, Jianqiao Robotics Machine Learning We present CoRMA(Contrastive Robotic Motor Adaptation), a context-based meta-adaptation framework that modifies RMA for force-dominant assembly. CoRMA replaces raw simulator-parameter adaptation with a compact 6D simulator-only semantic contact context describing contact onset, lateral engagement, guided transition, contact direction, and jamming. A deployable causal Transformer adapter infers this context online from force, proprioceptive, and action histories using semantic regression and a force-regime contrastive objective. At deployment, oracle context is removed and replaced by the inferred context, enabling within-episode adaptation without demonstrations, privileged inputs, or gradient updates. We evaluate CoRMA on PegInsert, GearMesh, and NutThread in Isaac Lab / Isaac Sim 5.0 and on a real Marvin arm. Compared with FORGE baselines that achieve high simulation success but degrade substantially on hardware, CoRMA retains higher verified real success under controlled target-pose noise. These results support semantic contact inference as a reusable adaptation interface within a related assembly task family, while broader unseen-task generalization and Real2Sim calibration remain future work. |
| title | CoRMA: Contrastive RMA for Contact-Rich Meta-Adaptation |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2605.22082 |