---
title: "能量结构潜在世界模型：面向物理一致开放世界运动规划的神经时间场"
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方程","具身AI","潜在世界模型","神经时间场","运动规划"]
---

# 能量结构潜在世界模型：面向物理一致开放世界运动规划的神经时间场

## AI 点评

> 这篇文章的价值不在于又刷了一个指标，而是把物理规律从隐式‘黑盒’变成显式‘白盒’，让世界模型真正学会可迁移的物理常识。对做机器人导航和安全决策的研究者来说，这套方案值得立刻复现；对做基础世界模型的人，也是个很好的启发。

## 速览

物理一致的运动规划是具身AI的核心挑战。现有潜在世界模型学习无约束的未来表征，物理规律隐含其中，难以形成可复用的物理知识，导致开放世界导航可靠性不足。为此，本文提出能量结构潜在世界模型（ELWM），在潜在状态中显式携带能量与动量，通过耗散和控制端口确保严格因果转换，并基于多模态RGB-D与惯性交互历史训练。进一步构建物理条件神经时间场（PC-NTF），将ELWM集成到到达时间场中，通过Eikonal方程生成物理信息导航策略。实验显示，相比通用潜在模型，运动预测NRMSE从0.36降至0.29；相比主动神经时间场，导航成功率从81.3%提升至89.7%，SPL从0.64提升至0.73，物理碰撞率从12.1%降至5.8%，Eikonal残差从0.083降至0.031。结果表明，将显式物理结构嵌入潜在空间可弥合预测世界模型与安全动态可行运动规划之间的鸿沟。

## 关键点

- 提出能量结构潜在世界模型（ELWM），在潜在空间显式建模能量与动量，并通过耗散与控制端口保证严格因果转换。
- 构建物理条件神经时间场（PC-NTF），利用Eikonal方程将ELWM集成到到达时间场，生成物理一致的导航策略。
- 在未见场景中，PC-NTF将0.8秒运动预测NRMSE从0.36降至0.29，导航成功率提升至89.7%，SPL提升至0.73，物理碰撞率降至5.8%。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_daed580a1d1045fd6f95db2f