English

Lifting Embodied World Models for Planning and Control

Computer Vision and Pattern Recognition 2026-04-30 v1 Artificial Intelligence Machine Learning

Abstract

World models of embodied agents predict future observations conditioned on an action taken by the agent. For complex embodiments, action spaces are high-dimensional and difficult to specify: for example, precisely controlling a human agent requires specifying the motion of each joint. This makes the world model hard to control and expensive to plan with as search-based methods like CEM scale poorly with action dimensionality. To address this issue, we train a lightweight policy that maps high-level actions to sequences of low-level joint actions. Composing this policy with the frozen world model produces a lifted world model that predicts a sequence of future observations from a single high-level action. We instantiate this framework for a human-like embodiment, defining the high-level action space as a small set of 2D waypoints annotated on the current observation frame, each specifying a near-term goal position for a leaf joint (pelvis, head, hands). Waypoints are low-dimensional, visually interpretable, and easy to specify manually or to search over. We show that the lifted world model substantially outperforms searching directly in low-level joint space (3.8×3.8\times lower mean joint error to the goal pose), while remaining more compute-efficient and generalizing to environments unseen by the policy.

Keywords

Cite

@article{arxiv.2604.26182,
  title  = {Lifting Embodied World Models for Planning and Control},
  author = {Alex N. Wang and Trevor Darrell and Pavel Izmailov and Yutong Bai and Amir Bar},
  journal= {arXiv preprint arXiv:2604.26182},
  year   = {2026}
}
R2 v1 2026-07-01T12:40:18.205Z