Strapdown inertial navigation system (SINS)/ ultra- short baseline (USBL) integrated navigation system is widely used in navigation and positioning of underwater vehicle. In an unknown and complex underwater environment, unstable USBL measurement information can lead to decreased navigation accuracy. In the traditional method, the interference to USBL is uniformly modeled as outliers, but in practice, it is also represented as slowly varying errors, update irregular errors. The latter two errors are not easy to be detected at the beginning of occurrence. Therefore, a SINS/USBL integrated navigation technology based on novel adaptive neural fuzzy inference system (ANFIS) is proposed. This model can detect and compensate abnormal USBL information and maximize USBL information. In order to improve the prediction accuracy of ANFIS, an ANFIS algorithm based on variational Bayesian Kalman filter and principal component analysis (PCA) is proposed to avoid the decrease of positioning accuracy caused by false compensation. The simulation shows that the designed ANFIS algorithm can accurately predict the above anomalies. And it can overcome the problem that USBL measurement anomalies are difficult to be detected at the initial stage. Combined with the proposed integrated navigation technology, it obtain the same positioning accuracy in complex environment as in good environment. The effectiveness and robustness of the proposed method are verified by river experiment.

Stable and reliable high-precision navigation and positioning is regarded as an urgent demand for marine intelligent transportation system. Medium and large autonomous underwater vehicles (AUVs) can be equipped with various navigation sensors to ensure positioning accuracy. In contrast, small AUVs have limited carrying capacity, and how to achieve reliable positioning for long endurance with more basic and necessary sensors is worthy of in-depth investigation. Therefore, a robust Doppler velocity log (DVL) aided inertial navigation strategy is designed in this survey. A tightly integrated system model based on DVL Doppler shift and ranging information aided inertial navigation system is established, which solves the problem of positioning performance degradation caused by error accumulation and beam failure in traditional methods. Based on consistency principle of sensor equipment, the system residual is identified by dead reckoning model and compensated for DVL terrain aided navigation, which solves the problem that systematic errors have great influence on nonlinear terrain and are difficult to identify. At the same time, the terrain entropy is introduced to design the confidence evaluation algorithm, which improves the adaptability of system in different terrain scenes. Simulation and lake test results show that the proposed method has higher positioning accuracy, reliability and stability, and is suitable for AUVs long-endurance navigation tasks.

With the increasing demand for marine monitoring, the use of coverage path planning based on unmanned aerial vehicle (UAV) aerial images to assist multiple unmanned surface vehicles (USVs) has shown great potential in marine applications. However, achieving accurate map modeling and optimal path planning are still key challenges that restrict its widespread application. To this end, an innovative coverage path planning algorithm for UAV-assisted multiple USVs is proposed. First, a semantic segmentation algorithm based on the YOLOv5-assisted prompting segment anything model (SAM) is designed to establish an accurate map model. By refining the axial, length, width, and coordinate information of obstacles, the algorithm enables YOLOv5 to generate accurate object bounding box prompts and then assists SAM in automatically and accurately extracting obstacles and coastlines in complex scenes. Based on this accurate map model, a multi-objective stepwise optimization coverage path planning algorithm is further proposed. The algorithm divides the complete path into two parts, the straight paths and the turning paths, and both the path length and the number of turns is designed, respectively, to optimize each type of path step by step, which significantly improves the coverage effect. Experiments prove that in various complex marine coverage scenarios, the proposed algorithm achieves 100% coverage, the redundancy rate is less than 2%, and it is superior to existing advanced algorithms in path length and number of turns. This research provides a feasible technical solution for efficient and accurate marine coverage tasks and lays the foundation for unmanned marine supervision.

The partial DVL measurement problem is attracting more and more attention in the coupling period of Strapdown Inertial Navigation System (SINS)/ Doppler Velocity Log (DVL) integration system. However, it is seldom discussed in SINS/DVL coarse alignment period, where full 3-dimensional velocity information is still a requisite for the existing attitude determination methods. To expand the initial alignment ability of SINS/DVL integration system under partial DVL measurements scenario, a novel beam velocity aided SINS in-motion coarse alignment solution is proposed in this work. First, an initial attitude determination model is derived with DVL beam outputs, where the relationship between the original beam Doppler shifts and the initial attitude is investigated, rather than the direct DVL velocity output. Then, a Cubature Kalman filter (CKF) based parameter estimation algorithm is explored for the nonlinear model. Simulation and field test data are employed to evaluate the performance of the proposed solution, where various DVL configurations and valid beam distributions are involved. The experiment results show the effectiveness of the presented mechanism, confirming the possibility of partial DVL aided SINS coarse alignment scheme.

Long-endurance, high-precision navigation and positioning of autonomous underwater vehicle (AUV) is regarded as an urgent need for marine intelligent transportation systems. However, the dead reckoning system alone cannot achieve such a task. The existing terrain aided navigation system is greatly affected by the terrain environment, and it is difficult to balance system complexity and positioning performance. Therefore, a tightly coupled terrain aided navigation strategy based on isogonal multibeam echosounder (MBES) modeling method is proposed. An integrated navigation system based on inertial navigation, MBES, and Doppler velocity log is designed, and a new isogonal multibeam echosounder modeling method based on two-step iteration is proposed, which improves the modeling problem of the system from the sensor level. Furthermore, a tightly coupled framework is proposed to realize the organic fusion of multi-sensor data, which can reduce the system scale and identify the internal errors of the system. Simulation and lake test results show that the proposed method has higher positioning accuracy, reliability, and stability. Accurate navigation and localization of the AUV can even be achieved with a lower resolution prior map, larger initial position error, and fewer particles.