# PO-PDDL: Learning Symbolic POMDPs from Visual Demonstrations for Robot Planning Under Uncertainty

arXiv: https://arxiv.org/abs/2606.15654 · HTML: https://mlsanity.com/paper/2606.15654/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 14 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners](https://mlsanity.com/paper/2307.01928/) (2023)
- [Large Language Models as Commonsense Knowledge for Large-Scale Task Planning](https://mlsanity.com/paper/2305.14078/) (2023)
- [DESPOT: Online POMDP Planning with Regularization](https://mlsanity.com/paper/1609.03250/) (2016)
- [VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents](https://mlsanity.com/paper/2510.16907/) (2025)
- [Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks](https://mlsanity.com/paper/2312.06876/) (2023)
- [Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models](https://mlsanity.com/paper/2407.12979/) (2024)
- [Generating Symbolic World Models via Test-time Scaling of Large Language Models](https://mlsanity.com/paper/2502.04728/) (2025)
- [LLM-Guided Probabilistic Program Induction for POMDP Model Estimation](https://mlsanity.com/paper/2505.02216/) (2025)
- [One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration](https://mlsanity.com/paper/2505.18382/) (2025)
- [UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning](https://mlsanity.com/paper/2507.21545/) (2025)
- [LLMs for Robotic Object Disambiguation](https://mlsanity.com/paper/2401.03388/) (2024)
- [Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs](https://mlsanity.com/paper/2506.02860/) (2025)
- [PlanU: Large Language Model Reasoning through Planning under Uncertainty](https://mlsanity.com/paper/2510.18442/) (2025)
- [CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Building](https://mlsanity.com/paper/2410.13756/) (2024)
- [Unifying Deep Predicate Invention with Pre-trained Foundation Models](https://mlsanity.com/paper/2512.17992/) (2025)
- [Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning](https://mlsanity.com/paper/2603.03704/) (2026)

## Abstract (arXiv)

Real-world robot task planning must operate under both stochastic action execution and partial observability, yet constructing Partially Observable Markov Decision Process (POMDP) models for real robotics domains remains difficult and labor-intensive. We introduce PO-PDDL, a symbolic formulation of POMDPs that preserves the relational structure and LLM-friendly syntax of the Planning Domain Definition Language (PDDL), while explicitly modeling partial observability, stochasticity, and beliefs. Building on this formulation, we propose a demonstration-driven pipeline for learning PO-PDDL models. The proposed method reconstructs latent symbolic state trajectories from real-robot execution videos, identifies partial observability via inconsistencies between inferred states and visual observations, and learns stochastic transition and observation models accordingly. The resulting PO-PDDL domains are reusable across tasks and enable online belief-space planning under both perception and execution uncertainty. Experiments on real-world long-horizon manipulation tasks show that our method consistently outperforms existing PDDL and POMDP model-learning approaches, achieving robust task planning under uncertainty with significantly lower planning cost.