SOURCE-LINKED INTELLIGENCE

Function-Preserving Data Generation for Zero-Shot Real-to-Sim-to-Real Manipulation

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Robotic data generation is a promising paradigm for scaling robot learning without collecting large-scale real-world data. However, generating geometrically diverse yet physically valid data for contact-rich tasks remains challenging, especially when success depends on precise geometric interfaces. Standard shape augmentation methods often distort task-critical interfaces, resulting in invalid contact relationships, e.g., fit mismatches or interpenetration, rendering downstream interactions infeasible. To address these limitations, we propose a function-preserving Real-to-Sim-to-Real framework

Read original source ↗ Open in workspace

recordType

paper

region

Global