Research
Robotics teams building manipulation systems can take simulation-to-real training approaches from this research as a reference point for reducing costly physical trial and error.
At the Conference on Robot Learning (CoRL), NVIDIA and partners are showing how robots can be trained in simulation for fine manipulation tasks such as aligning gears, connecting cables and assembling small components. The work marks a shift from earlier simulation-based training for locomotion, such as walking, rolling and hopping, toward more delicate tasks that require precise touch.
Read the full article at NVIDIA
CoFabrix summarises and comments on this story. The original reporting belongs to NVIDIA.
Find out where your organization stands -- and what to do about it.