首先叙述了自行研制的水下机器人的数据融合目的，通过分析水下智能机器人采用的传感器的性能，对各种传感器的信息进行可信度分配；然后采用Ｄｅｍｐｓｔｅｒ－Ｓｈａｆｅｒ证据理论方法，把各类传感信息作为证据，判断机器人前方是否存在障碍物 Firstly, the purpose of data fusion of self-developed underwater robots is described. By analyzing the performance of sensors used in underwater intelligent robots, the credibility of the information of all kinds of sensors is distributed. Then Dempster-Shafer theory of evidence is used to analyze all kinds of underwater robots. Sensory information as evidence to determine the presence of obstacles in front of the robot 