In this paper, through the application research of underwater gliders, it is found that ocean currents are the major influencing factor in the practical application of gliders. The objective of this study is to solve the path planning of glider formation in time-varying ocean currents. Using the existing glider model, energy consumption model and time-varying ocean current model are established based on the existing data, and a model close to the practical application of glider formation is established as well. The existing RRT algorithms are improved to be OCi-RRT (Ocean current improved RRT) algorithms based on environmental ocean currents. the algorithms are used to solve the path planning problems encountered in the practical application of gliders. Through simulations that are close to the restrictions of reality and the ideal communication state, it indicates that the improved RRT algorithms are suitable for path planning of glider formation in real ocean current environments. Then, a large number of simulation experiments are conducted, the results show that OCi-RRT* can reduce the number of cycles and path length by up to 14%, and the unit energy utilization can increase by up to 25% comparing with the RRT algorithm.

Cabin placement layout is an important part of ship cabin layout design. A good cabin placement layout can improve the efficiency of the ship’s cabin arrangement. However, optimisation of the layout of cabin placement is not widely studied and more often relies on the experience of the staff. Thus, a novel methodology combining systematic layout planning and a genetic algorithm to optimise the cabin placement is presented in this paper. First key elements are converted by a systematic planning method that is often applied in factory layout, and a preliminary cabin placement layout model is established according to these key elements. Then the circulation strength and adjacency strength are taken as sub-objectives to establish a mathematical model, and an improved genetic algorithm is used to optimise the model. The result of the optimisation is compared with the initial schemes to verify the validity of the algorithm. Finally, the human factors are introduced according to the actual situation. The AHP method is used to select the layout scheme of the cabin that is most likely to be applied in the actual cabin layout.

Motivated by the application of water-entry problems in the air-drop deployment of a spherical oceanographic measuring device, the free-fall water entry of a sphere was numerically investigated by using the transient Reynolds-averaged Navier–Stokes (RANS) method. A convergence study was carried out, which accounts for the mesh density and time-step independence. The present model was validated by the comparison of non-dimensional impact force with previous experimental and numerical results. Effects of parameters, such as impact velocity, radius, and mass of the sphere on the impact force and the acceleration of the sphere, are discussed. It is found that the peak value of the non-dimensional impact force is independent of the impact velocity and the radius of the sphere, while it depends on the mass of the sphere. By fitting the relationship between the peak value of the non-dimensional impact force and the non-dimensional mass, simplified formulas for the prediction of peak values of the impact force and the acceleration were achieved, which will be useful in the design of the spherical oceanographic measuring device.

Path planning technology is significant for planetary rovers that perform exploration missions in unfamiliar environments. In this work, we propose a novel global path planning algorithm, based on the value iteration network (VIN), which is embedded within a differentiable planning module, built on the value iteration (VI) algorithm, and has emerged as an effective method to learn to plan. Despite the capability of learning environment dynamics and performing long-range reasoning, the VIN suffers from several limitations, including sensitivity to initialization and poor performance in large-scale domains. We introduce the double value iteration network (dVIN), which decouples action selection and value estimation in the VI module, using the weighted double estimator method to approximate the maximum expected value, instead of maximizing over the estimated action value. We have devised a simple, yet effective, two-stage training strategy for VI-based models to address the problem of high computational cost and poor performance in large-size domains. We evaluate the dVIN on planning problems in grid-world domains and realistic datasets, generated from terrain images of a moon landscape. We show that our dVIN empirically outperforms the baseline methods and generalize better to large-scale environments.