Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot

TL;DR

Genie Sim 3.0 is a high-fidelity simulation platform for humanoid robots that uses LLMs to generate diverse environments and evaluate policies, facilitating scalable data collection and effective sim-to-real transfer.

Contribution

The paper introduces Genie Sim Generator, an LLM-powered tool for scene creation, and a benchmark for automated evaluation, advancing scalable robot learning and simulation fidelity.

Findings

Synthetic data enables effective zero-shot sim-to-real transfer.

LLM-driven scene generation supports diverse environment synthesis.

Automated evaluation pipeline improves benchmarking efficiency.

Abstract

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.