Lane-Level Map Matching based on HMM
Journal article, 2021

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

map matching

Viterbi algorithm

road networks

lane-level map matching

hidden Markov model


Anders Hansson

Zenuity AB

Ellen Korsberg

Student at Chalmers

Roza Maghsood

Zenuity AB

Eliza Nordén

Student at Chalmers

Selpi Selpi

Chalmers, Mechanics and Maritime Sciences (M2), Vehicle Safety

IEEE Transactions on Intelligent Vehicles

23798858 (eISSN)

Vol. 6 3 430-439

Subject Categories

Other Computer and Information Science

Other Engineering and Technologies

Probability Theory and Statistics

Computer Science

Areas of Advance

Information and Communication Technology


Driving Forces

Sustainable development



More information

Latest update

4/5/2022 5