Wayne Wu (@wayne_wu_0503)
2025-07-11 | โค๏ธ 472 | ๐ 72
๐URBAN-SIM is released! A large-scale robot learning platform for urban spaces, built on NVIDIA Omniverse. Train robots at scale in rich, interactive city environments. ๐ https://github.com/metadriverse/urban-sim
Key Features: โก๏ธ High Efficiency: Thousands of FPS on a single GPU โ enabling fast robot training. ๐ Scalable Training: Add more GPUs, scale up performance (FPS) continuously. ๐๏ธRich Scene Context: Infinite scene generation โ supporting tasks like visual locomotion, navigation, VLA training, and robot-human-scene interaction. ๐ฎ Versatile Interfaces. Collect data via VR headset, racing wheel, keyboard, or mouse for imitation learning. ๐งฉ Ecosystem Compatibility: Built on NVIDIA Omniverse, IsaacSim, and PhysX.
๐ Related
See similar notes in domain-robotics, domain-ai-ml