Open Source
WorldComposer: Generative High-Fidelity Simulation with Digital Cousins for Generalizable Robot Learning and Evaluation
arXiv cs.RO0 views
arXiv:2604.15805v2 Announce Type: replace 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.
Source:https://arxiv.org/abs/2604.15805PreviousAERR-Nav: Adaptive Exploration-Recovery-Reminiscing Strategy for Zero-Shot Object NavigationNextPose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation
Related posts
GTA VI — Rockstar made the game. ClipForge makes the clips.
0dev.to
I built Cornhole News. A Hacker News inspired site for news across the Midwest
0Hacker News
Launch HN: Onlook (YC W25) – An open-source developer tool for designers
0Hacker News
Gemini 4 Neon brings complex agent workflows to Copilot and Google's AI tools
0dev.to Machine Learning
December 24 Is the Newest Week on the WARN Layoff Calendar — 2,528 Workers Scheduled
0dev.to Career

2567. Minimum Score by Changing Two Elements
0dev.to PHP