Lane-Level Map Matching Based on HMM

Lane-level map matching is essential for autonomous driving. In this paper, we propose a Hidden Markov Model (HMM) trajectory of noisy GPS measurements to the road lanes in which vehicle records its positions. To our knowledge, first time that HMM used lane-level matching. Apart from values, model further assisted by yaw rate data (converted lane change indicator signal) and visual cues form left right marking types (dashed, solid, etc.). Having defined expressions emission transition probabilities, evaluate demonstrate it achieves 95.1% recall 3.3% median path length error motorway trajectories.