Multi-sensor Data Fusion Algorithm Based on Fuzzy Adaptive Kalman Filter

In order to resolve the problem of multi-sensor dynamic system with uncertain or changeable measurement noise, we present a multi-sensor data fusion algorithm based on fuzzy adaptive Kalman filter. Combined fuzzy logic and covariance-matching technique together to adjust the measurement noise covariance and make model measurement noise gradually close to the true noise level. As a result, the Kalman filter's tolerance to model error is improved. When the measurement data is missing or abnormal, the observation is replaced by the predicted one, and the divergence of the traditional Kalman filter is omitted. Then we use a multi-sensor optimal information fusion criterion weighted by matrices in the linear minimum variance sense. The simulation results show the proposed method is feasible and effective, and more accurate for target tracking. At the same time, we discuss the effect of the number of sensor on the estimation precision.