<ul><li>Self-supervised learning is used for developing traversability models for off-road navigation.</li><li>Existing methods utilize evidential deep learning to quantify model uncertainty.</li><li>PIETRA is a self-supervised learning framework that integrates physics priors into evidential neural networks.</li><li>PIETRA improves learning accuracy and navigation performance in environments with distribution shifts.</li></ul>

PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terrain

Discover more