Search papers, labs, and topics across Lattice.
3
0
4
3
Guaranteeing safety in diffusion-based trajectory planning is now possible by embedding a certifiable barrier function directly into the denoising loop, ensuring forward invariance and preserving the learned path geometry.
Representing perceptual uncertainty with Gaussian mixture models in robot navigation allows for less conservative and more adaptive motion planning while maintaining probabilistic safety guarantees.
Autonomous vehicles can actively reduce uncertainty and improve safety by gently nudging human drivers toward safer behaviors, rather than just passively reacting to their predicted actions.
