A adaptive map matching algorithm based on Fuzzy-Neural-Network for vehicle navigation system

Current vehicle navigation systems estimate the vehicle position from the Global Positioning System (GPS) signals and INS signals. However, because of the unknown GPS noise, the estimated position has an undesirable error. To solve this problem, a novel map matching method based on adaptive fuzzy-neural network (AFNN) is proposed in the paper, two important parameters are selected as the networks input signal, such as the projection distance from positioning point to candidate road and the comparability between positioning trajectory and candidate road. A four layers AFNN was designed based on if-then rule set, the convergent learning rule is fetched for the AFNN. Some experimental results show that the proposed algorithm has very good performance for matching the position of car to correct road under normal traffic conditions.