TY - JOUR A1 - Wöltche, Adrian T1 - Evolving map matching with markov decision processes N2 - Map matching is about finding the best route of a given track in a road network. This can be useful for many statistical analyses on mobility. With increasing spread of modern cars and mobile devices many tracks are available to match. The difficulty in map matching lies in the geospatial differences between tracks and road networks. Current technologies resolve such differences with Hidden Markov Models and Viterbi algorithm. They majorly vary concerning the used metrics for the probabilities in the models. In this research we improve map matching technology by refining the underlying algorithms, models and metrics. We will introduce Markov Decision Processes with Value Iteration and Q-Learning to the map matching domain and we will compare them to Hidden Markov Models with Viterbi algorithm. Markov Decision Processes allow to use active decisions and rewards, which are not available in previous methods. Combined with improvements concerning the preparation of tracks and the road network, and various technologies for improved processing speed, we will show on a publicly available map matching data set that our approach has a higher overall performance compared to previous map matching technology. We will eventually discuss more possibilities we enable with our approach. KW - map matching KW - geospatial information science KW - markov decision process KW - hidden markov model Y1 - 2021 UR - https://opus4.kobv.de/opus4-hof/frontdoor/index/index/docId/119 UR - https://nbn-resolving.org/urn:nbn:de:bvb:1051-opus4-1193 ER -