Adaptive Vehicle Cooperative Positioning System With Uncertain GPS Visibility and Neural Network-based Improved Approach

Position accuracy is a key factor to fulfill the requirements of several safety applications of vehicle networking, which will be a prospective application scenario for the Fifth Generation (5G) mobile communication system. In this paper, we present a cooperative localization system, implementing the data fusion of the observation from Received Signal Strength (RSS), Carrier Frequency Offset (CFO) and Global Positioning System (GPS) to enhance the tolerance against the situation of limited GPS visibility. A neural network-based algorithm is also introduced to optimize the accuracy of the cooperative localization system. Results of experiments and simulations demonstrate the improvement on the position stability and accuracy of the integrated system.