Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them

ArXi:2603.19852v1 Announce Type: cross Deep learning-based online mapping has emerged as a cornerstone of autonomous driving, yet these models frequently fail to generalize beyond familiar environments. We propose a framework to identify and measure the underlying failure modes by disentangling two effects: Memorization of input features and overfitting to known map geometries. We propose measures based on evaluation subsets that control for geographical proximity and geometric similarity between.