Method and system of ambiguity resolution and bias reduction for perception and map association

Abstract

A method includes receiving map data with a plurality of map lane edges and a plurality of perception lane edges of a roadway segment. The method includes determining a probability score of alignments that each indicate whether at least one of the map lane edges of the alignment is to be a same lane line as one of the perception lane edges of the alignment. The method includes resolving an ambiguity when no probability score of the roadway segment satisfies at least one alignment criterion, and determining a resolved alignment between the perception and map lane edges. This includes applying multiple ambiguity stages each with a different ambiguity test and that determine whether to increment a non-ambiguity count depending on the magnitude of likelihoods related to the alignments. The resolved alignment exists when the alignment between lane edges has a highest non-ambiguity count.