Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.19364 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908605955964928 |
|---|---|
| author | Raja, Golnaz Agishev, Ruslan Prágr, Miloš Pajarinen, Joni Zimmermann, Karel Singh, Arun Kumar Ghabcheloo, Reza |
| author_facet | Raja, Golnaz Agishev, Ruslan Prágr, Miloš Pajarinen, Joni Zimmermann, Karel Singh, Arun Kumar Ghabcheloo, Reza |
| contents | Uncertainty-aware robot motion prediction is crucial for downstream traversability estimation and safe autonomous navigation in unstructured, off-road environments, where terrain is heterogeneous and perceptual uncertainty is high. Most existing methods assume deterministic or spatially independent terrain uncertainties, ignoring the inherent local correlations of 3D spatial data and often producing unreliable predictions. In this work, we introduce an efficient probabilistic framework that explicitly models spatially correlated aleatoric uncertainty over terrain parameters as a probabilistic world model and propagates this uncertainty through a differentiable physics engine for probabilistic trajectory forecasting. By leveraging structured convolutional operators, our approach provides high-resolution multivariate predictions at manageable computational cost. Experimental evaluation on a publicly available dataset shows significantly improved uncertainty estimation and trajectory prediction accuracy over aleatoric uncertainty estimation baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ProTerrain: Probabilistic Physics-Informed Rough Terrain World Modeling Raja, Golnaz Agishev, Ruslan Prágr, Miloš Pajarinen, Joni Zimmermann, Karel Singh, Arun Kumar Ghabcheloo, Reza Robotics Uncertainty-aware robot motion prediction is crucial for downstream traversability estimation and safe autonomous navigation in unstructured, off-road environments, where terrain is heterogeneous and perceptual uncertainty is high. Most existing methods assume deterministic or spatially independent terrain uncertainties, ignoring the inherent local correlations of 3D spatial data and often producing unreliable predictions. In this work, we introduce an efficient probabilistic framework that explicitly models spatially correlated aleatoric uncertainty over terrain parameters as a probabilistic world model and propagates this uncertainty through a differentiable physics engine for probabilistic trajectory forecasting. By leveraging structured convolutional operators, our approach provides high-resolution multivariate predictions at manageable computational cost. Experimental evaluation on a publicly available dataset shows significantly improved uncertainty estimation and trajectory prediction accuracy over aleatoric uncertainty estimation baselines. |
| title | ProTerrain: Probabilistic Physics-Informed Rough Terrain World Modeling |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.19364 |