Robust Online Residual Refinement via Koopman-Guided Dynamics Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915496051343360 |
|---|---|
| author | Gong, Zhefei Lyu, Shangke Ding, Pengxiang Xiao, Wei Wang, Donglin |
| author_facet | Gong, Zhefei Lyu, Shangke Ding, Pengxiang Xiao, Wei Wang, Donglin |
| contents | Imitation learning (IL) enables efficient skill acquisition from demonstrations but often struggles with long-horizon tasks and high-precision control due to compounding errors. Residual policy learning offers a promising, model-agnostic solution by refining a base policy through closed-loop corrections. However, existing approaches primarily focus on local corrections to the base policy, lacking a global understanding of state evolution, which limits robustness and generalization to unseen scenarios. To address this, we propose incorporating global dynamics modeling to guide residual policy updates. Specifically, we leverage Koopman operator theory to impose linear time-invariant structure in a learned latent space, enabling reliable state transitions and improved extrapolation for long-horizon prediction and unseen environments. We introduce KORR (Koopman-guided Online Residual Refinement), a simple yet effective framework that conditions residual corrections on Koopman-predicted latent states, enabling globally informed and stable action refinement. We evaluate KORR on long-horizon, fine-grained robotic furniture assembly tasks under various perturbations. Results demonstrate consistent gains in performance, robustness, and generalization over strong baselines. Our findings further highlight the potential of Koopman-based modeling to bridge modern learning methods with classical control theory. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12562 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Online Residual Refinement via Koopman-Guided Dynamics Modeling Gong, Zhefei Lyu, Shangke Ding, Pengxiang Xiao, Wei Wang, Donglin Robotics Imitation learning (IL) enables efficient skill acquisition from demonstrations but often struggles with long-horizon tasks and high-precision control due to compounding errors. Residual policy learning offers a promising, model-agnostic solution by refining a base policy through closed-loop corrections. However, existing approaches primarily focus on local corrections to the base policy, lacking a global understanding of state evolution, which limits robustness and generalization to unseen scenarios. To address this, we propose incorporating global dynamics modeling to guide residual policy updates. Specifically, we leverage Koopman operator theory to impose linear time-invariant structure in a learned latent space, enabling reliable state transitions and improved extrapolation for long-horizon prediction and unseen environments. We introduce KORR (Koopman-guided Online Residual Refinement), a simple yet effective framework that conditions residual corrections on Koopman-predicted latent states, enabling globally informed and stable action refinement. We evaluate KORR on long-horizon, fine-grained robotic furniture assembly tasks under various perturbations. Results demonstrate consistent gains in performance, robustness, and generalization over strong baselines. Our findings further highlight the potential of Koopman-based modeling to bridge modern learning methods with classical control theory. |
| title | Robust Online Residual Refinement via Koopman-Guided Dynamics Modeling |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.12562 |