Saved in:
Bibliographic Details
Main Authors: Zook, Alex, Sun, Fan-Yun, Spjut, Josef, Blukis, Valts, Birchfield, Stan, Tremblay, Jonathan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.15536
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917046480011264
author Zook, Alex
Sun, Fan-Yun
Spjut, Josef
Blukis, Valts
Birchfield, Stan
Tremblay, Jonathan
author_facet Zook, Alex
Sun, Fan-Yun
Spjut, Josef
Blukis, Valts
Birchfield, Stan
Tremblay, Jonathan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15536
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GRS: Generating Robotic Simulation Tasks from Real-World Images
Zook, Alex
Sun, Fan-Yun
Spjut, Josef
Blukis, Valts
Birchfield, Stan
Tremblay, Jonathan
Robotics
Artificial Intelligence
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.
title GRS: Generating Robotic Simulation Tasks from Real-World Images
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2410.15536