paper-with-me

홈 › Papers

OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence

2026-05-12 · Jiajian Li, Jingyuan Huang, Junru Gong, Qi Wang, Xiaokang Yang, Yunbo Wang arxiv

We present OrbiSim, a novel robotic simulation paradigm that redefines world models as a fully differentiable physics engine for embodied intelligence. Unlike prior world models that focus on unconstrained imagination in latent or visual domains, OrbiSim establishes a unified, physically-grounded pathway that bridges structured scene assets, neural dynamics, and downstream reinforcement learning. By enabling end-to-end differentiability throughout the entire simulation loop -- spanning from explicit state transitions to visual observation generation -- OrbiSim supports tasks traditionally intractable for classical simulators, such as differentiable contact modeling, gradient-based policy optimization under sparse rewards, and intuitive physical inference. Empirical results demonstrate that OrbiSim significantly outperforms state-of-the-art world models in both predictive fidelity and control performance. Furthermore, its consistent responsiveness to asset configurations and physical parameters suggests its potential as a differentiable tool for enhancing robot simulation and policy training.

📄 PDF Abstract BibTeX arXiv:2605.16395

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Learning to See Physics via Visual De-animation

2017-12-01 · NeurIPS 2017 12 · Jiajun Wu, Erika Lu, Pushmeet Kohli, Bill Freeman 외

We introduce a paradigm for understanding physical scenes without human annotations. At the core of our system is a physical world representation that is first recovered by a perception module and then utilized by physic…

Future predictionState Estimation

A Recurrent Differentiable Engine for Modeling Tensegrity Robots Trainable with Low-Frequency Data

2022-02-28 · Kun Wang, Mridul Aanjaneya, Kostas Bekris

Tensegrity robots, composed of rigid rods and flexible cables, are difficult to accurately model and control given the presence of complex dynamics and high number of DoFs. Differentiable physics engines have been recent…

MuJoCo

Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets

2025-10-22 · Jiashi Feng, Xiu Li, Jing Lin, Jiahang Liu 외 arxiv

Developing embodied AI agents requires scalable training environments that balance content diversity with physics accuracy. World simulators provide such environments but face distinct limitations: video-based methods ge…

Scene Generation3D Generation

GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models

2026-08-06 · Shuai Wang, Yaxin Feng, Xuekun Jiang, Shihan Tian 외 arxiv

Physics engines facilitate large-scale training and evaluation for embodied intelligence, while generative video world models are emerging as implicit simulators of future states and interactions. However, existing evalu…

EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence

2025-06-12 · Xinjie Wang, Liu Liu, Yu Cao, Ruiqi Wu 외

Constructing a physically realistic and accurately scaled simulated 3D world is crucial for the training and evaluation of embodied intelligence tasks. The diversity, realism, low cost accessibility and affordability of …

Image to 3DLayout GenerationScene GenerationText to 3D+1