OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence

OrbiSim is a new robotic simulation paradigm that treats world models as a fully differentiable physics engine for embodied intelligence. It integrates structured scene assets, neural dynamics, and reinforcement learning into a single, physically grounded, end‑to‑end differentiable pipeline. The approach enables tasks such as differentiable contact modeling, gradient‑based policy optimization with sparse rewards, and intuitive physical inference, and it outperforms state‑of‑the‑art world models in predictive fidelity and control performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• reinforcement-learning
• robotics
• benchmarks