Research On The Hybrid Positioning Stratery For Vehicle In Urban Areas Using RFID

The Intelligent Transportation System (ITS) is capable of reducing the traffic jams in urban areas, thus the traffic conditions can be improved effectively. Recent years, using the ITS to solve transportation problem has become an important direction in future development of modern traffic. Vehicle positioning is essential to ITS in that vehicles could be scheduled effectively when the accurate position of them is available. Hence achieving precise and reliable vehicle positioning in urban areas is the main challenge for ITS.Global positioning system (GPS) is the most wildly used technology in the field of vehicle positioning. However, it fails to work when the GPS signal isn’t available in block areas such as urban canyon and tunnel, In order to solve this problem, this paper proposes a hybrid multi-sensor fusion strategy for vehicle positioning in urban using Radio Frequency identification (RFID) technology. First, the preliminary positioning algorithm is developed. Further, to improve the positioning performance, an interactive multiple model (IMM) fusion algorithm is developed to fuse the data from preliminary positioning results and low-cost in-vehicle sensors, such as electronic compasses, wheel speed sensors and gyro. Finally, the proposed strategy is evaluated through experiments. The main work is summarized as follows:1. The multi-sensor data acquisition platform is accomplished. It includes the hardware platform and the software, which accounts for multi-sensor data acquirement.2. The preliminary positioning algorithm is developed. The received signal strength is used as an indicator to calculate the distances between the RFID tags and reader, and then a Recrusive Least Square (RLS) is designed to provide the preliminary position information for subsequent global fusion.3. The data from RFID and low-cost in-vehicle sensors is fused using IMM. To improve the positioning performance of fusion strategy, the kinematic model of land vehicle is established and then the interacting multiple model algorithm is developed to fuse the data from RFID and other in-vehicle sensors.4. The proposed strategy is evaluated through experiments. Those experiments include that the static test and the preliminary trial as well as the fusion trial.The main work of this paper has been accomplished. The results of experiments validate the feasibility and effectiveness of the proposed strategy, which is capable of acquiring high -accuracy position of vehicle in urban areas.