GPS and micro-electro-mechanical (MEMS) inertial systems have complementary qualities that make integrated navigation systems more robust. The effective integration of GPS and MEMS sensors is still challenging task for low cost navigation system. Kalman filters are widely used for sensor data fusion and navigation in mobile robotics. Taking in account GPS and inertial data processing problem nonlinearity, the Extended Kalman Filter (EKF) is used. One of the most important tasks in integration of GPS/INS is to choose the realistic dynamic model covariance matrix Q and measurement noise covariance matrix R for use in the Kalman filter. Adaptive algorithms automatically adjust Kalman filter system and measurement noise covariance matrix parameters taking in account navigation process performance i.e. position error. In this paper innovation based adaptive EKF for adapting R and Q was used in order to improve navigation system performance during GPS signal outages