English

GRS: Generating Robotic Simulation Tasks from Real-World Images

Robotics 2025-10-29 v3 Artificial Intelligence

Abstract

We introduce GRS (Generating Robotic Simulation tasks), a system addressing real-to-sim for robotic simulations. GRS creates digital twin simulations from single RGB-D observations with solvable tasks for virtual agent training. Using vision-language models (VLMs), our pipeline operates in three stages: 1) scene comprehension with SAM2 for segmentation and object description, 2) matching objects with simulation-ready assets, and 3) generating appropriate tasks. We ensure simulation-task alignment through generated test suites and introduce a router that iteratively refines both simulation and test code. Experiments demonstrate our system's effectiveness in object correspondence and task environment generation through our novel router mechanism.

Keywords

Cite

@article{arxiv.2410.15536,
  title  = {GRS: Generating Robotic Simulation Tasks from Real-World Images},
  author = {Alex Zook and Fan-Yun Sun and Josef Spjut and Valts Blukis and Stan Birchfield and Jonathan Tremblay},
  journal= {arXiv preprint arXiv:2410.15536},
  year   = {2025}
}
R2 v1 2026-06-28T19:28:56.998Z