It is difficult to maintain the exact location of mobile objects due to the limited resources in a mobile network. A consequence of this problem is that the update cost for a location-dependent continuous query for moving objects can be quite high using traditional methods. In this paper, we propose a probabilistic update method to maintain the fidelity of the query results without incurring significant update cost. Our scheme makes use of two types of updates, one to keep the uncertainty of the mobile object’s position within a specific confidence interval, and the other using probability that the moving object’s location uncertainty will affect the query result as the threshold to decide whether an update should be generated or not. The effectiveness of our approach is demonstrated using a series of simulation experiments.