When controlling a mobile robot using speech commands, the user's mistake or the recognizer's mis-recognition causes the robot to move in an unintended way, which can be dangerous. Therefore, we aim to develop a method for the robot to know if the robot's behavior matches the user's intention or not from the features of the speech commands. To this end, we investigated prosodic features in the command utterance given to a mobile robot when the robot does an intended or unintended behavior. As a result, we found that speaking rate of the speech under the robot's unintended behavior becomes slower, and the F0 becomes higher. In addition, we investigate if fatigue or experience affects the prosodic features, and we found that the F0 and intensity under the robot's unintended behavior were significantly different at the beginning of the experiment.