MIT: LucidSim training system helps robots close Sim2Real gap
Robotics Business Review
NOVEMBER 17, 2024
Previous approaches often relied on depth sensors, which simplified the problem but missed crucial real-world complexities.” To cook up their data, the team generated realistic images by extracting depth maps, which provide geometric information, and semantic masks, which label different parts of an image, from the simulated scene.
Let's personalize your content