# DWMP: Leveraging Dual World Models for Humanoid Obstacle Traversal

arXiv: https://arxiv.org/abs/2609.12347 · HTML: https://mlsanity.com/paper/2609.12347/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Humanoid and legged locomotion world models, one of 11 directions in World models.
- Builds on 4 of its 42 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Placed in

- World models / [Humanoid and legged locomotion world models](https://mlsanity.com/wm/humanoid-and-legged-locomotion-world-models/)

## Builds on (most cited first, 4 of 4)

- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [VB-Com: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception](https://mlsanity.com/paper/2502.14814/) (2025)
- [Ego-Vision World Model for Humanoid Contact Planning](https://mlsanity.com/paper/2510.11682/) (2025)
- [Koopman Dreamer: Spectrally Constrained Latent Dynamics for Stable World-Model Imagination](https://mlsanity.com/paper/2607.19719/) (2026)

## Abstract (arXiv)

Humanoid robots must traverse cluttered obstacle fields using onboard proprioceptive and visual observations, yet existing methods usually process multimodal observations without explicitly considering their different characteristics: proprioceptive observations are low-dimensional but governed by highly nonlinear robot dynamics, while egocentric visual observations are high-dimensional, noisy, and redundant. We propose DWMP (Dual World Model Policy), a framework that provides the actor with separate but complementary world-model representations for humanoid obstacle traversal. A Koopman-based dynamics world model lifts proprioceptive observations into a latent space where their temporal evolution is approximately linear, making the dynamics features easier for the actor to learn from. An RSSM-based visual world model compresses egocentric depth observations into compact stochastic states while preserving obstacle-related geometry. The student policy receives the fused latent representation for action generation, combining linearized proprioceptive dynamics with compressed visual perception. Experiments in simulation and on a Unitree G1 humanoid robot show that DWMP improves obstacle traversal performance over baselines and supports real-world deployment under randomized obstacle layouts.