A new fault-tolerant estimation method of unmanned aerial vehicle (UAV) dynamics in the presence of sensor/actuator faults with both adaptivity and robustness is proposed. This chapter addresses the subject of making a choice between the adaptive and robust methods when sensor/actuator faults occur. An adaptive method with Q-adaptation and robust method with R-adaptation are presented. Fault detection in the Kalman filter is based on the chi-square distribution of the normalized quadratic innovation function (NQI). After the detection of faults, it is proposed to run simultaneously both R-adaptive and Q-adaptive Kalman filters and compare their estimation performances to distinguish the sensor and actuator faults.