Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.07457 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914458946764800 |
|---|---|
| author | Cheng, Ziyang Wei, Haoyu Yin, Hang Xu, Xiuwei Yu, Bingyao Zhou, Jie Lu, Jiwen |
| author_facet | Cheng, Ziyang Wei, Haoyu Yin, Hang Xu, Xiuwei Yu, Bingyao Zhou, Jie Lu, Jiwen |
| contents | While decoupled control schemes for legged mobile manipulators have shown robustness, learning holistic whole-body control policies for tracking global end-effector poses remains fragile against Out-of-Distribution (OOD) inputs induced by sensor noise or infeasible user commands. To improve robustness against these perturbations without sacrificing task performance and continuity, we propose Competence Manifold Projection (CMP). Specifically, we utilize a Frame-Wise Safety Scheme that transforms the infinite-horizon safety constraint into a computationally efficient single-step manifold inclusion. To instantiate this competence manifold, we employ a Lower-Bounded Safety Estimator that distinguishes unmastered intentions from the training distribution. We then introduce an Isomorphic Latent Space (ILS) that aligns manifold geometry with safety probability, enabling efficient O(1) seamless defense against arbitrary OOD intents. Experiments demonstrate that CMP achieves up to a 10-fold survival rate improvement in typical OOD scenarios where baselines suffer catastrophic failure, incurring under 10% tracking degradation. Notably, the system exhibits emergent ``best-effort'' generalization behaviors to progressively accomplish OOD goals by adhering to the competence boundaries. Result videos are available at: https://shepherd1226.github.io/CMP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_07457 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection Cheng, Ziyang Wei, Haoyu Yin, Hang Xu, Xiuwei Yu, Bingyao Zhou, Jie Lu, Jiwen Robotics Artificial Intelligence Machine Learning While decoupled control schemes for legged mobile manipulators have shown robustness, learning holistic whole-body control policies for tracking global end-effector poses remains fragile against Out-of-Distribution (OOD) inputs induced by sensor noise or infeasible user commands. To improve robustness against these perturbations without sacrificing task performance and continuity, we propose Competence Manifold Projection (CMP). Specifically, we utilize a Frame-Wise Safety Scheme that transforms the infinite-horizon safety constraint into a computationally efficient single-step manifold inclusion. To instantiate this competence manifold, we employ a Lower-Bounded Safety Estimator that distinguishes unmastered intentions from the training distribution. We then introduce an Isomorphic Latent Space (ILS) that aligns manifold geometry with safety probability, enabling efficient O(1) seamless defense against arbitrary OOD intents. Experiments demonstrate that CMP achieves up to a 10-fold survival rate improvement in typical OOD scenarios where baselines suffer catastrophic failure, incurring under 10% tracking degradation. Notably, the system exhibits emergent ``best-effort'' generalization behaviors to progressively accomplish OOD goals by adhering to the competence boundaries. Result videos are available at: https://shepherd1226.github.io/CMP. |
| title | CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.07457 |