Proposed Technique to Improve VANET ’ s Vehicle Localization Accuracy in Multipath Environment

Localization (location estimation) of a vehicle in Vehicular Ad-hoc Network (VANET) has been studied n many fields since it has the ability to provide a v ariety of services like navigation, vehicle trackin g and collision detection etc. Global Positioning System (GPS) and Inertial Navigation System (INS) both are very usef l method of localization. By using Kalman Filter it is possi ble to combine these two systems to get better accu r y of localization. Now day’s typical localization techni ques combines GPS receiver measurement and measurem ents of the vehicle’s motion by INS. However, when the vehi cle traveling through an environment that creates a multipath effect, these techniques fail to produce the high l ocalization accuracy that they attain in an open en viro ments because of loss of satellite signal in a multipath area, such as areas with high buildings, trees, or tunnels. In this new advance localization technique is proposed to impro ve l calization accuracy. Also Artificial Neural Ne twork is used to detect multipath environment and then by using N elder Mead Optimization method we can reduce the lo calization error of a vehicle when it travelling through multi path environment.