Real-to-Sim Work Explodes as New Tool Automates Robot Scene Import

chris_j_paxton · x · 2026-07-29

Experts note an explosion of "real-to-sim" work in robotics, as it is crucial for development.

Robot training primarily relies on Imitation Learning (IL) and Reinforcement Learning (RL). IL requires expensive teleoperation or human demonstration data and tends to be brittle. RL requires physically accurate simulation environments. Traditionally, building these sims demanded manual 3D modeling or relying on pre-existing asset libraries.

To solve this, a new tool now allows developers to import custom assets, scenes, and physics into a simulation quickly and easily, paving the way for faster RL training.

Related event: World Labs Launches R2S2R Platform to Train Robots with Spatial Intelligence(6 posts)→

Original post →

More from Embodied

Embodied channel →