Procedural Generation of Articulated Simulation-Ready Assets

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Joshi, Abhishek, Han, Beining, Nugent, Jack, Saez-Diez, Max Gonzalez, Zuo, Yiming, Liu, Jonathan, Wen, Hongyu, Alexandropoulos, Stamatis, Kayan, Karhan, Calveri, Anna, Sun, Tao, Liu, Gaowen, Shao, Yi, Raistrick, Alexander, Deng, Jia
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918174201479168
author Joshi, Abhishek
Han, Beining
Nugent, Jack
Saez-Diez, Max Gonzalez
Zuo, Yiming
Liu, Jonathan
Wen, Hongyu
Alexandropoulos, Stamatis
Kayan, Karhan
Calveri, Anna
Sun, Tao
Liu, Gaowen
Shao, Yi
Raistrick, Alexander
Deng, Jia
author_facet Joshi, Abhishek
Han, Beining
Nugent, Jack
Saez-Diez, Max Gonzalez
Zuo, Yiming
Liu, Jonathan
Wen, Hongyu
Alexandropoulos, Stamatis
Kayan, Karhan
Calveri, Anna
Sun, Tao
Liu, Gaowen
Shao, Yi
Raistrick, Alexander
Deng, Jia
contents We introduce Infinigen-Articulated, a toolkit for generating realistic, procedurally generated articulated assets for robotics simulation. We include procedural generators for 18 common articulated object categories along with high-level utilities for use creating custom articulated assets in Blender. We also provide an export pipeline to integrate the resulting assets along with their physical properties into common robotics simulators. Experiments demonstrate that assets sampled from these generators are effective for movable object segmentation, training generalizable reinforcement learning policies, and sim-to-real transfer of imitation learning policies.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10755
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Procedural Generation of Articulated Simulation-Ready Assets
Joshi, Abhishek
Han, Beining
Nugent, Jack
Saez-Diez, Max Gonzalez
Zuo, Yiming
Liu, Jonathan
Wen, Hongyu
Alexandropoulos, Stamatis
Kayan, Karhan
Calveri, Anna
Sun, Tao
Liu, Gaowen
Shao, Yi
Raistrick, Alexander
Deng, Jia
Robotics
Graphics
We introduce Infinigen-Articulated, a toolkit for generating realistic, procedurally generated articulated assets for robotics simulation. We include procedural generators for 18 common articulated object categories along with high-level utilities for use creating custom articulated assets in Blender. We also provide an export pipeline to integrate the resulting assets along with their physical properties into common robotics simulators. Experiments demonstrate that assets sampled from these generators are effective for movable object segmentation, training generalizable reinforcement learning policies, and sim-to-real transfer of imitation learning policies.
title Procedural Generation of Articulated Simulation-Ready Assets
topic Robotics
Graphics
url https://arxiv.org/abs/2505.10755