Virtual global positioning system construction approach for unmanned surface vessel based on Dempster–Shafer theory and broad learning framework

Abstract Integrated navigation systems made up of a strap-down inertial navigation system (SINS) and global positioning system (GPS) are increasingly being used to improve the position, speed, and attitude information of unmanned surface vessels (USV). However, a GPS outage could occur due to the dependence of GPS performance on the external environment and the number of available satellites. This study uses an innovative combination of Dempster–Shafer (DS) theory and broad learning (BL) method to design a SINS/GPS integrated navigation system. First, the velocity and position information derived from the SINS and their corresponding GPS were fused using DS fusion rules, while the SINS error was modelled using the BL method. A ‘virtual’ GPS was then designed using the proposed DS–BL approach to provide the speed and position information when the GPS signal was interrupted, thereby ensuring the continuous navigation of the USV. The results of both simulation and sea trial demonstrate that the proposed virtual GPS estimation approach is effective, and the navigational accuracy of the proposed method is superior to other methods.