Search papers, labs, and topics across Lattice.
Shanghai AI Lab
2
0
4
2
Forget painstakingly collecting real-world data for deformable object manipulation: SIM1 achieves equivalent policy performance with 15x less data by grounding simulations in the physical world.
Zero-shot visuotactile policies trained in a fast, parallelized simulator can directly control real robots in contact-rich tasks.
