A Novel Approach for GPS/INS Integration using Recurrent Neural Network with Evolutionary Optimization Techniques

摘要

Integration of Global Positioning System (GPS) and Inertial Navigation System (INS) has been extensively used in aircraft applications like autopilot, to provide better navigation, even in the absence of GPS. Even though Kalman Filter (KF) based GPS/INS integration provides a robust solution to navigation, it requires prior knowledge of the error model of INS, which increases the complexity of the system. Hence Neural Networks (NN) based GPS/INS integration are available in literature. But the NN based solutions have problems such as convergence and inaccuracy. To get better convergence ability the Recurrent Neural Network like Jordan Neural Network is proposed. Normally Back propagation Algorithm (BPA) is used to train the Recurrent Neural Network. But BP algorithm has disadvantages such as slow convergence rate and inaccuracy due to local minima. To overcome these problems, Evolutionary Algorithms like Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) trained Jordan Neural Network is proposed to get better position accuracy of the target. In this work, GPS/INS integration based on neural networks like Back Propagation Neural Network (BPNN) and Jordan Neural Network using BPA, GA and PSO are also analyzed and their performance parameters are compared.