In order to improve the positioning accuracy of the unmanned distribution vehicle, the GPS/BDS and IMU multi-sensor fusion technology is applied to the positioning system of the unmanned distribution vehicle. To solve the problems of low positioning accuracy and poor anti-interference which caused by signal loss and cumulative error in GPS / BDS and IMU positioning solution. In this paper, CKF algorithm is used to filter the positioning results from GPS/BDS and sins. That it will improve the positioning accuracy. When the GPS/BDS positioning receiving module signal is missing, combine IMU which provides data set and SINS algorithm to get the current position of the unmanned distribution vehicle; In dealing with the cumulative error in IMU positioning process, CKF is used to correct the GPS/BDS receiver data. In order to verify the superiority of the positioning solution method integrating GPS/BDS and IMU, a single BDS positioning system is used in the experiment to compare the positioning results. The results show that the method used in this paper reduces the speed error by 27.89% and the position error by 38.81%, which can effectively improve the positioning accuracy and stability of the unmanned distribution vehicle in the process of delivering goods.