Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911627487477760 |
|---|---|
| author | Yin, Chenghao Huang, Da Yang, Di Wang, Jichao Zhao, Nanshu Xu, Chen Sun, Wenjun Hou, Linjie Li, Zhijun Wu, Junhui Liu, Zhaobo Xiao, Zhen Zhang, Sheng Bao, Lei Feng, Rui Pang, Zhenquan Li, Jiayu Wang, Qian Yao, Maoqing |
| author_facet | Yin, Chenghao Huang, Da Yang, Di Wang, Jichao Zhao, Nanshu Xu, Chen Sun, Wenjun Hou, Linjie Li, Zhijun Wu, Junhui Liu, Zhaobo Xiao, Zhen Zhang, Sheng Bao, Lei Feng, Rui Pang, Zhenquan Li, Jiayu Wang, Qian Yao, Maoqing |
| contents | The development of robust and generalizable robot learning models is critically contingent upon the availability of large-scale, diverse training data and reliable evaluation benchmarks. Collecting data in the physical world poses prohibitive costs and scalability challenges, and prevailing simulation benchmarks frequently suffer from fragmentation, narrow scope, or insufficient fidelity to enable effective sim-to-real transfer. To address these challenges, we introduce Genie Sim 3.0, a unified simulation platform for robotic manipulation. We present Genie Sim Generator, a large language model (LLM)-powered tool that constructs high-fidelity scenes from natural language instructions. Its principal strength resides in rapid and multi-dimensional generalization, facilitating the synthesis of diverse environments to support scalable data collection and robust policy evaluation. We introduce the first benchmark that pioneers the application of LLM for automated evaluation. It leverages LLM to mass-generate evaluation scenarios and employs Vision-Language Model (VLM) to establish an automated assessment pipeline. We also release an open-source dataset comprising more than 10,000 hours of synthetic data across over 200 tasks. Through systematic experimentation, we validate the robust zero-shot sim-to-real transfer capability of our open-source dataset, demonstrating that synthetic data can server as an effective substitute for real-world data under controlled conditions for scalable policy training. For code and dataset details, please refer to: https://github.com/AgibotTech/genie_sim. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_02078 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot Yin, Chenghao Huang, Da Yang, Di Wang, Jichao Zhao, Nanshu Xu, Chen Sun, Wenjun Hou, Linjie Li, Zhijun Wu, Junhui Liu, Zhaobo Xiao, Zhen Zhang, Sheng Bao, Lei Feng, Rui Pang, Zhenquan Li, Jiayu Wang, Qian Yao, Maoqing Robotics The development of robust and generalizable robot learning models is critically contingent upon the availability of large-scale, diverse training data and reliable evaluation benchmarks. Collecting data in the physical world poses prohibitive costs and scalability challenges, and prevailing simulation benchmarks frequently suffer from fragmentation, narrow scope, or insufficient fidelity to enable effective sim-to-real transfer. To address these challenges, we introduce Genie Sim 3.0, a unified simulation platform for robotic manipulation. We present Genie Sim Generator, a large language model (LLM)-powered tool that constructs high-fidelity scenes from natural language instructions. Its principal strength resides in rapid and multi-dimensional generalization, facilitating the synthesis of diverse environments to support scalable data collection and robust policy evaluation. We introduce the first benchmark that pioneers the application of LLM for automated evaluation. It leverages LLM to mass-generate evaluation scenarios and employs Vision-Language Model (VLM) to establish an automated assessment pipeline. We also release an open-source dataset comprising more than 10,000 hours of synthetic data across over 200 tasks. Through systematic experimentation, we validate the robust zero-shot sim-to-real transfer capability of our open-source dataset, demonstrating that synthetic data can server as an effective substitute for real-world data under controlled conditions for scalable policy training. For code and dataset details, please refer to: https://github.com/AgibotTech/genie_sim. |
| title | Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot |
| topic | Robotics |
| url | https://arxiv.org/abs/2601.02078 |