TraversabilityIntermediate
From Language Priors to Field Adaptation: Preference Learning for Traversability Estimation
This preprint presents a traversability estimator that models terrain preferences as von Mises-Fisher prototypes in a frozen vision-language feature space, initialized from language rules and fine-tuned with sparse relative image annotations. It achieves competitive accuracy with end-to-end trained models on WayFAST, e.g., HDR 0.5 of 21.8% vs 22.5% for the SOTA, while improving sample efficiency and using only about 8.2k trainable parameters. This matters because it enables rapid domain adaptation for outdoor mobile robots without extensive per-platform annotation.