EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI
- Published
- Source
- arXiv
- Paper number
- 584
- Field
- Robotics
- arXiv ID
- 2607.07459
Key points
- It proposes a unified sim-ready representation that combines metric geometry, collision geometry, physical parameters, and affordance annotations in a single asset.
- Its model-agnostic asset pipeline connects TRELLIS, SAM3D, and Hunyuan3D as plugins and automates mesh repair, convex decomposition, and texture baking.
- The task-driven scene graph decomposes a natural-language task into spatial constraints over the robot, background, objects to manipulate, and distractors, then generates physically stable 6-DoF placements.
- Vibe Coding implements a stateful agent-skill harness that turns natural-language commands into physically validated bounded edits and then exports them to the simulator.
- It supports cross-simulator export to MuJoCo, Isaac Sim, Genesis, SAPIEN, and Bullet in USD, MJCF, and URDF formats.
- Online RL validation shows that training VLA policies on the generated environments raises simulation success from 9.7 percent to 79.8 percent and real-robot success from 21.7 percent to 75.0 percent.
Paper links
External research summaries. These are not HDATF publications or measured product results.