A navigation grade Strapdown Inertial Navigation System (SINS) combined with a Doppler Velocity Log (DVL) is widely used for autonomous navigation of underwater vehicles. Whether the DVL is able to provide continuous velocity measurements is of crucial importance to the integrated navigation precision. Considering that the DVL may fail during the missions, a novel neural network-based SINS/DVL integrated navigation approach is proposed. The nonlinear autoregressive exogenous (NARX) neural network, which is able to provide reliable predictions, is employed. While the DVL is available, the neural network is trained by the body frame velocity and its increment from the SINS and the DVL measurements. Once the DVL fails, the well trained network is able to forecast the velocity which can be used for the subsequent navigation. From the experimental results, it is clearly shown that the neural network is able to provide reliable velocity predictions for about 200 s–300 s during DVL malfunction and hence maintain the short-term accuracy of the integrated navigation.

Astronomical positioning and orientation are important components of astronomical geodesy tasks, and they could also be used for real-time celestial navigation. In traditional methods, astronomical positioning and astronomical orientation can only be implemented separately, and all the observations with different levels of precision are given the same weight. To change this, a unified astronomical positioning and orientation model based on robust estimation was developed. First, the problem that the coordinate rotation parameters are difficult to calculate directly was solved by using the Rodrigues matrix. Consequently, the astronomical longitude, latitude, and azimuth can be calculated at the same time. Second, as a result of the introduction of a robust estimation method, specific weight is matched to observations with corresponding precision when calculating the parameters, and thus more accurate astronomical longitude, latitude, and azimuth valuation can be calculated simultaneously. Experiments indicate that the unified model was able not only to achieve astronomical positioning and orientation simultaneously but also improve the accuracy of final results.