Motion Planning And Trajectory Generation

via “trajectory-augmentation-and-synthesis”

Dataset by nvidia. 3,34,635 downloads.

Unique: Implements physics-aware trajectory augmentation for GR00T-X data with action perturbation, state interpolation, and video transforms, enabling synthetic trajectory generation that respects robot kinematics

vs others: More principled than naive augmentation because physics constraints are enforced, and more efficient than collecting new robot data because augmentation is fully algorithmic