# UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning

arXiv: https://arxiv.org/abs/2507.21545 · HTML: https://mlsanity.com/paper/2507.21545/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2025.

## Built on by (most cited first, 5 of 5)

- [PLanAR: Planning-Language-Grounded Agentic Reasoning for Robot Manipulation](https://mlsanity.com/paper/2602.01662/) (2026)
- [RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments](https://mlsanity.com/paper/2610.12424/) (2026)
- [PO-PDDL: Learning Symbolic POMDPs from Visual Demonstrations for Robot Planning Under Uncertainty](https://mlsanity.com/paper/2606.15654/) (2026)
- [PDDL-ART: Autonomous Symbolic Abstraction From Demonstration For Long-Horizon Robotic Manipulation Using Vision-Language Models](https://mlsanity.com/paper/2608.17146/) (2026)
- [VIDEAS: Distilling Explicit Action Semantics from Demonstration Videos for World Models via Prior-Guided Simulation](https://mlsanity.com/paper/2609.33464/) (2026)

## Abstract (arXiv)

Robotic task planning in real-world environments requires reasoning over implicit constraints from language and vision. While LLMs and VLMs offer strong priors, they struggle with long-horizon structure and symbolic grounding. Existing methods that combine LLMs with symbolic planning often rely on handcrafted or narrow domains, limiting generalization. We propose UniDomain, a framework that pre-trains a PDDL domain from robot manipulation demonstrations and applies it for online robotic task planning. It extracts atomic domains from 12,393 manipulation videos to form a unified domain with 3137 operators, 2875 predicates, and 16481 causal edges. Given a target class of tasks, it retrieves relevant atomics from the unified domain and systematically fuses them into high-quality meta-domains to support compositional generalization in planning. Experiments on diverse real-world tasks show that UniDomain solves complex, unseen tasks in a zero-shot manner, achieving up to 58% higher task success and 160% improvement in plan optimality over state-of-the-art LLM and LLM-PDDL baselines.