A new GPU-accelerated deformable simulation framework trains manipulation policies in minutes using only synthetic data, achieving robust zero-shot transfer to physical robots.
Small steps in physics simulation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.RO 2roles
method 1polarities
use method 1representative citing papers
Isaac Gym achieves 2-3 orders of magnitude faster robot policy training by keeping physics simulation and PyTorch-based RL entirely on GPU with direct buffer sharing.
citing papers explorer
-
FLASH: Fast Learning via GPU-Accelerated Simulation for High-Fidelity Deformable Manipulation in Minutes
A new GPU-accelerated deformable simulation framework trains manipulation policies in minutes using only synthetic data, achieving robust zero-shot transfer to physical robots.
-
Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
Isaac Gym achieves 2-3 orders of magnitude faster robot policy training by keeping physics simulation and PyTorch-based RL entirely on GPU with direct buffer sharing.