599 | Page Comparative Study of Map Matching Algorithms - GPS Vehicle Navigation Technology Mr.R.Manikandan 1 , Dr.R.Latha 2 1 Ph.D Research Scholar, Computer Applications, St.Peter’s University, Chennai. 2 Prof & Head., Dept of Computer Applications, St.Peter’s University, Chennai. ABSTRACT: Several map-matching algorithm techniques have been developed to improve vehicle positioning in navigation technology, using Global Positioning System (GPS) data and other wireless sensors. This paper deals with a comparative study of existing map-matching algorithm for GPS positioning and vehicle navigation. The main objectives of this paper are to gather knowledge about existing map matching algorithms. Especially Hidden Markov model, Weight based Model and other map matching algorithms. The Hidden Markov Model is a statistical model with two states a) Observed State, b) Unobserved State, well known for providing solutions to temporal recognition applications such as text and speech recognition. Weight based map matching algorithm is the high accuracy for segment assignment using minimum input variables of latitude and longitude of the vehicles. We mainly classified process of HMM, Weight based and other Map matching algorithm as comparative study, which is mainly implemented in the urban cities. Keywords: GPS, Map Matching, Navigation. I. INTRODUCTION Map Matching algorithm which is used to Map the Physical Location using GPS. Map matching is a technique combining electronic map with locating information to obtain the real position of vehicles in a road network Map-matching is a basic operation for improving positioning accuracy by integrating positioning data with spatial road network data to identify the correct road link on which a vehicle is travelling and to determine the location of a vehicle on a road link. An Algorithm which is used to find the exact location of vehicle or particular position of an object is called Map Matching algorithm. Manikandan et al., (2017) Map Matching algorithm are divided into two categories: one is offline where the data are processed after the data are recorded and other is online, where the data are processed during recording time. Map-matching algorithm is actually a pattern identification process. Map-matching algorithms can be categorized into four groups: geometric map matching, topological map matching, probabilistic map matching and other advanced techniques. The geometric map-matching algorithm was introduced by Bernstein and Kornhauser, M.A. Quddus et al., (2016). This algorithm contains point-to-point matching, point-to-curve matching, and curve-to-curve matching and improved geometric map matching. Point-to-point and point-to-curve matching don’t fully make