Automization of an INS/GPS intecrated system using genetic optimization

Most integrated inertial navigation systems (INS) and global positioning systems (GPS) have been implemented using the Kalman filtering technique with its drawbacks related to the need for predefined INS error model, immunity to noise effects and observability. Most recently, an INS/GPS integration method using a hybrid-adaptive-neuro-fuzzy integration system (ANFIS) has been proposed by the authors. The advantage of the ANFIS over other classical filtering algorithms is its ability to deal with noise in the input data in dynamic environments. During the availability of GPS signal, the ANFlS is trained to map the error between the GPS and the INS. The ANFIS will then be employed to predict the error of the INS position components during GPS signal blockage. As ANFIS will be used in real time applications, the change in the system parameters (e.g. the number of membership functions, the step size, arid step increase and decrease rates) to achieve the minimum training error during cach time period is automated. This paper introduces a genetic optimization algorithm that is used to update the ANFlS parameters with the INS/GPS error function used as the objective function to be minimized. Challenges encountered in the integration process are discussed and the proposed architecture is tested in a land vehicle navigation. GPS signal outage of a time period of 120 seconds was simulated during 1420 seconds of land vehicle navigation. The experimental results demonstrated the advantages of the genetically optimized ANFlS For lNS/GPS Integration.