Perception-Based Beliefs for POMDPs with Visual Observations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912881538236416 |
|---|---|
| author | Schäfers, Miriam Krale, Merlijn Simão, Thiago D. Jansen, Nils Weininger, Maximilian |
| author_facet | Schäfers, Miriam Krale, Merlijn Simão, Thiago D. Jansen, Nils Weininger, Maximilian |
| contents | Partially observable Markov decision processes (POMDPs) are a principled planning model for sequential decision-making under uncertainty. Yet, real-world problems with high-dimensional observations, such as camera images, remain intractable for traditional belief- and filtering-based solvers. To tackle this problem, we introduce the Perception-based Beliefs for POMDPs framework (PBP), which complements such solvers with a perception model. This model takes the form of an image classifier which maps visual observations to probability distributions over states. PBP incorporates these distributions directly into belief updates, so the underlying solver does not need to reason explicitly over high-dimensional observation spaces. We show that the belief update of PBP coincides with the standard belief update if the image classifier is exact. Moreover, to handle classifier imprecision, we incorporate uncertainty quantification and introduce two methods to adjust the belief update accordingly. We implement PBP using two traditional POMDP solvers and empirically show that (1) it outperforms existing end-to-end deep RL methods and (2) uncertainty quantification improves robustness of PBP against visual corruption. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05679 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Perception-Based Beliefs for POMDPs with Visual Observations Schäfers, Miriam Krale, Merlijn Simão, Thiago D. Jansen, Nils Weininger, Maximilian Machine Learning Partially observable Markov decision processes (POMDPs) are a principled planning model for sequential decision-making under uncertainty. Yet, real-world problems with high-dimensional observations, such as camera images, remain intractable for traditional belief- and filtering-based solvers. To tackle this problem, we introduce the Perception-based Beliefs for POMDPs framework (PBP), which complements such solvers with a perception model. This model takes the form of an image classifier which maps visual observations to probability distributions over states. PBP incorporates these distributions directly into belief updates, so the underlying solver does not need to reason explicitly over high-dimensional observation spaces. We show that the belief update of PBP coincides with the standard belief update if the image classifier is exact. Moreover, to handle classifier imprecision, we incorporate uncertainty quantification and introduce two methods to adjust the belief update accordingly. We implement PBP using two traditional POMDP solvers and empirically show that (1) it outperforms existing end-to-end deep RL methods and (2) uncertainty quantification improves robustness of PBP against visual corruption. |
| title | Perception-Based Beliefs for POMDPs with Visual Observations |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.05679 |