ZeST: A VLM-based Zero-Shot Traversability Navigation for Unknown Environments
arXiv:2508.19131v4 Announce Type: replace-cross Abstract: Advances in robotics and autonomous navigation systems hinge on the ability to predict terrain traversability accurately. Traditional methods for generating datasets to train these prediction models often involve putting robots into potentially hazardous environments, posing risks to equipment and safety. To solve this problem, we present ZeST, a novel approach that treats repeated VLM outputs as stochastic measurements and fuses them in…