RoboBrain 2.0: See Better. Think Harder. Do Smarter.

🗞️ News

• 2025-07-23: 🤗 RoboBrain 2.0-3B model checkpoint has been released in Huggingface.
• 2025-07-03: 🤗 RoboBrain 2.0-32B model checkpoint has been released in Huggingface.
• 2025-06-07: 🎉 We highlight the training framework (FlagScale) developed by BAAI Framework R&D team, and the evaluation framework (FlagEvalMM) by BAAI FlagEval team. Both are used for RoboBrain 2.0.
• 2025-06-06: 🤗 RoboBrain 2.0-7B model checkpoint has been released in Huggingface..
• 2025-06-06: 🔥 We're excited to announce the release of our more powerful RoboBrain 2.0.
• 2025-04-11: 🎉 RoboBrain 1.0 was selected for CVPR 2025's official Embodied AI Trends Commentary.
• 2025-02-27: 🌍 RoboBrain 1.0 was accepted to CVPR2025.

🔥 Overview

We are thrilled to announce the launch of RoboBrain 2.0, the most powerful open-source embodied brain model to date. Compared to its predecessor, RoboBrain 1.0, the new version is designed to unify perception, reasoning, and planning for complex embodied tasks in physical environments. RoboBrain 2.0 comes in three variants: an ultra-lightweight 3B model, a lightweight 7B model, and a full-scale 32B model, all featuring a heterogeneous architecture with a vision encoder and a language model. Despite its compact size, RoboBrain 2.0 delivers exceptional performance across a wide range of embodied reasoning tasks. The newly released 3B model is optimized for resource-constrained scenarios, being extremely lightweight and easy to deploy, with spatial understanding capabilities comparable to the 7B model, making it ideal for edge devices and real-time applications. The 7B model strikes a balance between performance and computational requirements, suitable for diverse scenarios, while the 32B model achieves leading results in most spatial and temporal benchmarks, surpassing prior open-source and proprietary models. RoboBrain 2.0 supports critical real-world embodied intelligence capabilities, including spatial understanding (e.g., affordance prediction, spatial referring, trajectory forecasting) and temporal decision-making (e.g., closed-loop interaction, multi-agent long-horizon planning, and real-time scene memory). This report details the model architecture, data construction, multi-stage training strategies, infrastructure, and practical applications. We hope RoboBrain 2.0 advances embodied AI research and serves as a practical step toward building generalist embodied agents.

📆 Todo

• Release model checkpoint for RoboBrain 2.0-3B
• Release model checkpoint for RoboBrain 2.0-7B
• Release quick inference example for RoboBrain 2.0
• Release training codes for RoboBrain 2.0
• Release model checkpoint for RoboBrain 2.0-32B

🚀 Features

RoboBrain 2.0 supports interactive reasoning with long-horizon planning and closed-loop feedback, spatial perception for precise point and bbox prediction from complex instructions, temporal perception for future trajectory estimation, and scene reasoning through real-time structured memory construction and update.

⭐️ Architecture

RoboBrain 2.0 supports multi-image, long video, and high-resolution visual inputs, along with complex task instructions and structured scene graphs on the language side. Visual inputs are processed via a Vision Encoder and MLP Projector, while textual inputs are tokenized into a unified token stream. All inputs are fed into a LLM Decoder that performs long-chain-of-thought reasoning and outputs structured plans, spatial relations, and both relative and absolute coordinates.

🤗 Model Zoo

🛠️ Setup

# clone repo.
git clone https://github.com/FlagOpen/RoboBrain2.0.git
cd RoboBrain

# build conda env.
conda create -n robobrain2 python=3.10
conda activate robobrain2
pip install -r requirements.txt

🤖 Simple Inference

Note: Please refer to RoboBrain 2.0 Github for the usage of RoboBrain 2.0

😊 More Results

Benchmark comparison across spatial reasoning and temporal task planning. RoboBrain2.0 achieves state-of-the-art (SOTA) or near-SOTA performance on nine spatial reasoning benchmarks: BLINK-Spatial, CV-Bench, EmbSpatial, RoboSpatial, RefSpatial, SAT, VSI-Bench, Where2Place and ShareRobot-Bench, and three temporal reasoning benchmarks: Multi-Robot-Planning, Ego-Plan2 and RoboBench-Planning, It not only outperforms leading open-source models such as Cosmos-Reason1 and Qwen2.5-VL, but also surpasses closed-source models like Gemini 2.5 Pro, o4-mini and Claude Sonnet 4.

📑 Citation

If you find this project useful, welcome to cite us.

@article{RoboBrain 2.0,
    title={RoboBrain 2.0 Technical Report},
    author={BAAI RoboBrain Team},
    journal={arXiv preprint arXiv:2507.02029},
    year={2025}
}

@article{RoboBrain 1.0,
    title={Robobrain: A unified brain model for robotic manipulation from abstract to concrete},
    author={Ji, Yuheng and Tan, Huajie and Shi, Jiayu and Hao, Xiaoshuai and Zhang, Yuan and Zhang, Hengyuan and Wang, Pengwei and Zhao, Mengdi and Mu, Yao and An, Pengju and others},
    journal={arXiv preprint arXiv:2502.21257},
    year={2025}
}

@article{RoboOS,
    title={RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration},
    author={Tan, Huajie and Hao, Xiaoshuai and Lin, Minglan and Wang, Pengwei and Lyu, Yaoxu and Cao, Mingyu and Wang, Zhongyuan and Zhang, Shanghang},
    journal={arXiv preprint arXiv:2505.03673},
    year={2025}
}

@article{zhou2025roborefer,
    title={RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics},
    author={Zhou, Enshen and An, Jingkun and Chi, Cheng and Han, Yi and Rong, Shanyu and Zhang, Chi and Wang, Pengwei and Wang, Zhongyuan and Huang, Tiejun and Sheng, Lu and others},
    journal={arXiv preprint arXiv:2506.04308},
    year={2025}
}

@article{Reason-RFT,
    title={Reason-rft: Reinforcement fine-tuning for visual reasoning},
    author={Tan, Huajie and Ji, Yuheng and Hao, Xiaoshuai and Lin, Minglan and Wang, Pengwei and Wang, Zhongyuan and Zhang, Shanghang},
    journal={arXiv preprint arXiv:2503.20752},
    year={2025}
}

@article{Code-as-Monitor,
    title={Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection},
    author={Zhou, Enshen and Su, Qi and Chi, Cheng and Zhang, Zhizheng and Wang, Zhongyuan and Huang, Tiejun and Sheng, Lu and Wang, He},
    journal={arXiv preprint arXiv:2412.04455},
    year={2024}
}

Acknowledgements

We sincerely thank RoboRefer (NeurIPS 2025) for bringing powerful spatial reasoning and referring capabilities to RoboBrain 2.0, and Reason-RFT (NeurIPS 2025) for providing an effective reinforcement learning post-training method.