CARLA

Researchers propose using latent space generative world models to help autonomous vehicles handle unexpected situations, reducing reliance on vast training data. The approach integrates a neural netwo…

Researchers have developed PersonaDrive, a pipeline that conditions vision-language-action driving agents on retrieved demonstrations from a style-instructed human driving dataset to produce aggressiv…

Researchers have developed DiffSlack, a differentiable projection layer that enforces nonlinear inequality constraints in neural networks by reformulating them as equalities with learnable slack varia…