---
title: "Energy-Structured Latent World Models with Neural Time Fields for Physically Consistent Open-World Motion Planning"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.09876v1"
permalink: "https://feed.astralor.com/items/itm_daed580a1d1045fd6f95db2f"
published: "2026-08-10T17:31:18.000Z"
score: 78
channel: "ai"
tags: ["Eikonal Equation","Embodied AI","Latent World Model","Neural Time Fields","Motion Planning"]
---

# Energy-Structured Latent World Models with Neural Time Fields for Physically Consistent Open-World Motion Planning

## AI commentary

> The value of this paper lies not in another state-of-the-art result, but in turning implicit physics into explicit structure within world models, enabling transferable physical commonsense. For researchers in robot navigation and safe decision-making, this approach is worth immediate reproduction; for those working on foundational world models, it offers a compelling new direction.

## At a glance

Physically consistent motion planning remains a fundamental challenge in embodied AI, as generated trajectories must strictly conform to real-world execution dynamics. While latent world models offer a promising approach by predicting these dynamics, existing methods learn unconstrained future representations where absorbed physics remains implicit. Therefore, they fail to form reusable physical knowledge, which compromises reliability in unpredictable open-world navigation. To address this, we propose a novel Energy-Structured Latent World Model (ELWM). Our key idea is to structure the ELWM latent state to explicitly carry energy and momentum, ensuring strictly causal transitions via dissipation and control ports. Trained on multimodal RGB-D and inertial interaction histories, our model guarantees physically consistent predictions. We further implement this for motion planning by constructing Physics-Conditioned Neural Time Fields (PC-NTF), a key technical cornerstone that integrates ELWM into an arrival time field via the Eikonal equation to yield a physically-informed navigation policy. Across held-out scenes, our evaluation reveals significant improvements. Compared to generic latent models, PC-NTF reduces 0.8-s motion-prediction NRMSE from 0.36 to 0.29. Against Active Neural Time Fields, it improves navigation success from 81.3% to 89.7% and SPL from 0.64 to 0.73, while cutting the physical collision rate from 12.1% to 5.8% and the Eikonal residual from 0.083 to 0.031. Beyond these targeted gains, our results demonstrate that embedding explicit physical structures into latent spaces intrinsically bridges the gap between predictive world models and safe, dynamically feasible motion planning.

## Key points

- Proposes Energy-Structured Latent World Model (ELWM) that explicitly encodes energy and momentum in latent space, ensuring strictly causal transitions via dissipation and control ports.
- Constructs Physics-Conditioned Neural Time Fields (PC-NTF), integrating ELWM into an arrival time field via the Eikonal equation for physically-informed navigation policy.
- On held-out scenes, PC-NTF reduces 0.8-s motion-prediction NRMSE from 0.36 to 0.29, improves navigation success to 89.7%, SPL to 0.73, and cuts physical collision rate to 5.8%.

## Full text

Physically consistent motion planning remains a fundamental challenge in embodied AI, as generated trajectories must strictly conform to real-world execution dynamics. While latent world models offer a promising approach by predicting these dynamics, existing methods learn unconstrained future representations where absorbed physics remains implicit. Therefore, they fail to form reusable physical knowledge, which compromises reliability in unpredictable open-world navigation. To address this, we propose a novel Energy-Structured Latent World Model (ELWM). Our key idea is to structure the ELWM latent state to explicitly carry energy and momentum, ensuring strictly causal transitions via dissipation and control ports. Trained on multimodal RGB-D and inertial interaction histories, our model guarantees physically consistent predictions. We further implement this for motion planning by constructing Physics-Conditioned Neural Time Fields (PC-NTF), a key technical cornerstone that integrates ELWM into an arrival time field via the Eikonal equation to yield a physically-informed navigation policy. Across held-out scenes, our evaluation reveals significant improvements. Compared to generic latent models, PC-NTF reduces 0.8-s motion-prediction NRMSE from 0.36 to 0.29. Against Active Neural Time Fields, it improves navigation success from 81.3% to 89.7% and SPL from 0.64 to 0.73, while cutting the physical collision rate from 12.1% to 5.8% and the Eikonal residual from 0.083 to 0.031. Beyond these targeted gains, our results demonstrate that embedding explicit physical structures into latent spaces intrinsically bridges the gap between predictive world models and safe, dynamically feasible motion planning.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_daed580a1d1045fd6f95db2f