# STRIPS-WM: Learning Grounded Propositional STRIPS-style World Models from Images

arXiv: https://arxiv.org/abs/2606.06832 · HTML: https://mlsanity.com/paper/2606.06832/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 6 of 6)

- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Contrastive Learning of Structured World Models](https://mlsanity.com/paper/1911.12247/) (2019)
- [Learning First-Order Symbolic Representations for Planning from the Structure of the State Space](https://mlsanity.com/paper/1909.05546/) (2019)
- [Universal Planning Networks](https://mlsanity.com/paper/1804.00645/) (2018)
- [From Real World to Logic and Back: Learning Generalizable Relational Concepts For Long Horizon Robot Planning](https://mlsanity.com/paper/2402.11871/) (2024)
- [Learning Discrete Abstractions for Visual Rearrangement Tasks Using Vision-Guided Graph Coloring](https://mlsanity.com/paper/2509.14460/) (2025)

## Abstract (arXiv)

Robots performing long-horizon visual manipulation observe high-dimensional images, but successful plans depend on action-relevant facts: what can be done now and what changes afterward. A useful planning representation should discard irrelevant visual details while preserving action applicability and effects. Classical task planners exploit this structure through symbolic operators with preconditions and effects, but obtaining such representations from raw visual experience remains challenging. We study a visual task-planning setting in which a robot receives only image transitions: the current image, executed high-level action, and the resulting image. At test time, given a start image and a goal image, the robot must produce a sequence of high-level actions that reaches the goal. To address this problem, we introduce STRIPS-WM, a framework for learning image-grounded STRIPS-style world models directly from visual transitions. STRIPS-WM first induces a finite abstract transition graph from images, then learns latent binary predicates and one grounded propositional operator per action label. The learned operators form a symbolic action model with sparse preconditions and add/delete effects. Finally, the learned predicates are distilled into a visual encoder, enabling classical planning directly from novel start and goal images. Experiments on visual rearrangement tasks show that STRIPS-WM improves image-to-plan success over the tested visual rollout, latent graph-search and latent-symbolic baselines.