AI 中文总结
针对开放世界运动规划的物理一致性挑战，提出能量结构化潜在世界模型ELWM，结合物理条件神经时间场PC-NTF，显著提升了运动预测精度与导航成功率，降低了碰撞率与残差。
AI 中文摘要
物理一致性运动规划仍是具身人工智能的核心挑战，因为生成的轨迹必须严格符合现实世界的执行动力学。尽管潜在世界模型通过预测这些动力学提供了一种有前景的方法，但现有方法学习的是无约束的未来表示，其中物理吸收仍是隐含的，因此无法形成可复用的物理知识，这会损害不可预测开放世界导航的可靠性。为解决这一问题，我们提出了一种新颖的能量结构化潜在世界模型（Energy-Structured Latent World Model，ELWM）。我们的核心思路是将ELWM的潜在状态结构化，使其明确承载能量与动量，通过耗散和控制端口确保严格的因果转换。我们的模型在多模态RGB-D与惯性交互历史上进行训练，可保证物理一致性预测。我们进一步将其应用于运动规划，构建了物理条件神经时间场（Physics-Conditioned Neural Time Fields，PC-NTF），这是将ELWM通过 eikonal 方程集成到到达时间场以生成物理感知导航策略的关键技术基石。在保留的场景中，我们的评估显示出显著的改进：与通用潜在模型相比，PC-NTF将0.8秒运动预测的归一化均方根误差（NRMSE）从0.36降至0.29；与主动神经时间场（Active Neural Time Fields）相比，它将导航成功率从81.3%提升至89.7%，路径效率（SPL）从0.64提升至0.73，同时将物理碰撞率从12.1%降至5.8%，eikonal残差从0.083降至0.031。除这些针对性的提升外，我们的结果表明，将显式物理结构嵌入潜在空间从本质上缩小了预测世界模型与安全、动态可行运动规划之间的差距。
英文摘要
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.
Comments9 pages, 5 figures
