DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jia, Yufei, Wang, Guangyu, Dong, Yuhang, Wu, Junzhe, Zeng, Yupei, Lin, Haonan, Wang, Zifan, Ge, Haizhou, Gu, Weibin, Ding, Kairui, Yan, Zike, Cheng, Yunjie, Li, Yue, Wang, Ziming, Li, Chuxuan, Sui, Wei, Shi, Lu, Tian, Guanzhong, Huang, Ruqi, Zhou, Guyue
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918107237318656
author Jia, Yufei
Wang, Guangyu
Dong, Yuhang
Wu, Junzhe
Zeng, Yupei
Lin, Haonan
Wang, Zifan
Ge, Haizhou
Gu, Weibin
Ding, Kairui
Yan, Zike
Cheng, Yunjie
Li, Yue
Wang, Ziming
Li, Chuxuan
Sui, Wei
Shi, Lu
Tian, Guanzhong
Huang, Ruqi
Zhou, Guyue
author_facet Jia, Yufei
Wang, Guangyu
Dong, Yuhang
Wu, Junzhe
Zeng, Yupei
Lin, Haonan
Wang, Zifan
Ge, Haizhou
Gu, Weibin
Ding, Kairui
Yan, Zike
Cheng, Yunjie
Li, Yue
Wang, Ziming
Li, Chuxuan
Sui, Wei
Shi, Lu
Tian, Guanzhong
Huang, Ruqi
Zhou, Guyue
contents We present the first unified, modular, open-source 3DGS-based simulation framework for Real2Sim2Real robot learning. It features a holistic Real2Sim pipeline that synthesizes hyper-realistic geometry and appearance of complex real-world scenarios, paving the way for analyzing and bridging the Sim2Real gap. Powered by Gaussian Splatting and MuJoCo, Discoverse enables massively parallel simulation of multiple sensor modalities and accurate physics, with inclusive supports for existing 3D assets, robot models, and ROS plugins, empowering large-scale robot learning and complex robotic benchmarks. Through extensive experiments on imitation learning, Discoverse demonstrates state-of-the-art zero-shot Sim2Real transfer performance compared to existing simulators. For code and demos: https://air-discoverse.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21981
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments
Jia, Yufei
Wang, Guangyu
Dong, Yuhang
Wu, Junzhe
Zeng, Yupei
Lin, Haonan
Wang, Zifan
Ge, Haizhou
Gu, Weibin
Ding, Kairui
Yan, Zike
Cheng, Yunjie
Li, Yue
Wang, Ziming
Li, Chuxuan
Sui, Wei
Shi, Lu
Tian, Guanzhong
Huang, Ruqi
Zhou, Guyue
Robotics
68T40
I.2.9
We present the first unified, modular, open-source 3DGS-based simulation framework for Real2Sim2Real robot learning. It features a holistic Real2Sim pipeline that synthesizes hyper-realistic geometry and appearance of complex real-world scenarios, paving the way for analyzing and bridging the Sim2Real gap. Powered by Gaussian Splatting and MuJoCo, Discoverse enables massively parallel simulation of multiple sensor modalities and accurate physics, with inclusive supports for existing 3D assets, robot models, and ROS plugins, empowering large-scale robot learning and complex robotic benchmarks. Through extensive experiments on imitation learning, Discoverse demonstrates state-of-the-art zero-shot Sim2Real transfer performance compared to existing simulators. For code and demos: https://air-discoverse.github.io/.
title DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments
topic Robotics
68T40
I.2.9
url https://arxiv.org/abs/2507.21981