Energy-Structured Latent World Models with Neural Time Fields for Physically Constistent Open-World Motion Planning
2026-08-10 • Robotics
RoboticsArtificial Intelligence
AI summaryⓘ
The authors focus on making robot motion planning more physically accurate by explicitly modeling energy and momentum in their world predictions. They introduce a new model called ELWM that keeps track of physical properties to ensure that predicted movements obey real-world physics. This model is integrated into a navigation approach called PC-NTF, which improves planning by better predicting arrival times and avoiding collisions. Their experiments show that this method predicts motion more accurately and leads to safer, more successful navigation than previous methods. Overall, the authors demonstrate that adding physical structure to predictions helps bridge the gap between simulation and real-world robot movement.
latent world modelenergy and momentummotion planningembodied AIEikonal equationRGB-D sensingnavigation policycollision avoidancetime fieldsphysical dynamics
Authors
Yapeng Liu, Yuanzhao Zhai, Bo Ding, Huaimin Wang, Lin Wang
Abstract
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.