| # UnifoLM-WMA-0: A World-Model-Action (WMA) Framework under UnifoLM Family | |
| <div align="justify"> | |
| <b>UnifoLM-WMA-0</b> is Unitree‘s first open-source world-model–action architecture spanning multiple types of robotic embodiments, designed specifically for general-purpose robot learning. Its core component is a world-model capable of understanding the physical interactions between robots and the environments. This world-model provides two key functions: (a) <b>Simulation Engine</b> – operates as an interactive simulator to generate synthetic data for robot learning; (b) <b>Policy Enhancement</b> – connects with an action head and, by predicting future interaction processes with the world-model, further optimizes decision-making performance. | |
| </div> | |
| ## 🦾 Real Robot Deployment | |
| | <img src="assets/real_z1_stackbox.gif" style="border:none;box-shadow:none;margin:0;padding:0;" /> | <img src="assets/real_dual_stackbox.gif" style="border:none;box-shadow:none;margin:0;padding:0;" /> | | |
| |:---:|:---:| | |
| | <img src="assets/real_cleanup_pencils.gif" style="border:none;box-shadow:none;margin:0;padding:0;" /> | <img src="assets/real_g1_pack_camera.gif" style="border:none;box-shadow:none;margin:0;padding:0;" /> | | |
| **Note: the top-right window shows the world model’s prediction of future environmental changes.** | |
| ## License | |
| The model is released under the CC BY-NC-SA 4.0 license as found in the [LICENSE](https://huggingface.co/unitreerobotics/UnifoLM-WMA-0/blob/main/LICENSE). You are responsible for ensuring that your use of Unitree AI Models complies with all applicable laws. | |
| ## Model Architecture | |
|  | |