arXiv cs.AI· Jasper Lu, Zhenhao Shen, Yuanfei Wang, Shugao Liu, Shengqiang Xu, Shawn Xie, Jingkai Xu, Feng Jiang, Jade Yang, Chen Xie, Ruihai Wu·· 2 小时前AI 评分41
WorldComposer:结合 Digital Cousins 的生成式高保真仿真,面向可泛化机器人学习与评估
WorldComposer: Generative High-Fidelity Simulation with Digital Cousins for Generalizable Robot Learning and Evaluation
AI 导读
WorldComposer 是一个自动化生成式 Real2Sim2Real 框架,可将真实世界全景图转化为高保真、任务就绪的仿真环境,并通过场景与物体变化合成多样化的 Digital Cousins。
正文 · 原文
Authors:Jasper Lu, Zhenhao Shen, Yuanfei Wang, Shugao Liu, Shengqiang Xu, Shawn Xie, Jingkai Xu, Feng Jiang, Jade Yang, Chen Xie, Ruihai Wu
Abstract:Learning robust robot policies in real-world environments requires diverse data augmentation, yet scaling real-world data collection is costly due to the need for acquiring physical assets and reconfiguring environments. Therefore, augmenting real-world scenes into simulation has become a practical augmentation for efficient learning and evaluation. We present WorldComposer, an automated generative Real2Sim2Real framework that maps real-world panoramas into high-fidelity, task-ready simulation environments and further synthesizes diverse Digital Cousins through scene and object variations. Combined with high-quality physics engines and realistic assets, WorldComposer supports interactive manipulation across rigid, articulated, and deformable objects. Additionally, we incorporate multi-room stitching to construct consistent large-scale environments for long-horizon tasks. Experiments demonstrate a strong sim-to-real correlation validating our platform's fidelity, and show that extensively scaling up data generation leads to significantly better generalization to unseen scene and object variations, demonstrating the effectiveness of Digital Cousins for generalizable robot learning and evaluation.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2604.15805 [cs.RO] |
| (or arXiv:2604.15805v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2604.15805 arXiv-issued DOI via DataCite |
Submission history
From: Jiabao Lu [view email]
[v1]
Fri, 17 Apr 2026 08:06:26 UTC (13,636 KB)
[v2]
Wed, 18 Nov 2026 11:17:17 UTC (39,924 KB)
来源:arXiv cs.AI · arxiv.org