We present a sonar localization method using ubiquitous sensor network for autonomous water pollution monitoring fish robots. Autonomous tracking is one of important functions in mobile underwater vehicles which monitor water pollution indices. When fish robots find obstacles on its path, proper direction changes to avoid collision are necessary. Otherwise, they should follow the given tracks as close as possible to obtain a pollution map. For efficient tracking performance and procedures of surveying water areas, fish robots use GPS and a sonar system to find exact localization. Although GPS is a fundamental tool to obtain positional information, it is not the best choice in our system due to large errors. Fish robots need to have more precise localization methods. In this paper, we propose to employ USN motes with sonar system to transmit ultrasonic sound to calculate precise positional information. Our experimental results show that fish robots obtain more detailed positional information and make better tracking performance in the real situation.