Parameter-Robust MPPI for Safe Online Learning of Unknown Parameters
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_ | 1866911356913975296 |
|---|---|
| author | Vahs, Matti Choi, Jaeyoun Schmid, Niklas Tumova, Jana Fan, Chuchu |
| author_facet | Vahs, Matti Choi, Jaeyoun Schmid, Niklas Tumova, Jana Fan, Chuchu |
| contents | Robots deployed in dynamic environments must remain safe even when key physical parameters are uncertain or change over time. We propose Parameter-Robust Model Predictive Path Integral (PRMPPI) control, a framework that integrates online parameter learning with probabilistic safety constraints. PRMPPI maintains a particle-based belief over parameters via Stein Variational Gradient Descent, evaluates safety constraints using Conformal Prediction, and optimizes both a nominal performance-driven and a safety-focused backup trajectory in parallel. This yields a controller that is cautious at first, improves performance as parameters are learned, and ensures safety throughout. Simulation and hardware experiments demonstrate higher success rates, lower tracking error, and more accurate parameter estimates than baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_02948 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Parameter-Robust MPPI for Safe Online Learning of Unknown Parameters Vahs, Matti Choi, Jaeyoun Schmid, Niklas Tumova, Jana Fan, Chuchu Robotics Robots deployed in dynamic environments must remain safe even when key physical parameters are uncertain or change over time. We propose Parameter-Robust Model Predictive Path Integral (PRMPPI) control, a framework that integrates online parameter learning with probabilistic safety constraints. PRMPPI maintains a particle-based belief over parameters via Stein Variational Gradient Descent, evaluates safety constraints using Conformal Prediction, and optimizes both a nominal performance-driven and a safety-focused backup trajectory in parallel. This yields a controller that is cautious at first, improves performance as parameters are learned, and ensures safety throughout. Simulation and hardware experiments demonstrate higher success rates, lower tracking error, and more accurate parameter estimates than baselines. |
| title | Parameter-Robust MPPI for Safe Online Learning of Unknown Parameters |
| topic | Robotics |
| url | https://arxiv.org/abs/2601.02948 |