With the development of sensor technology, sensor nodes are increasingly being used in underwater environments. The strategy presented in this paper is designed to solve the problem of using a limited number of autonomous underwater vehicles (AUVs) to complete tasks such as data collection from sensor nodes when the number of AUVs is less than the number of target sensors. A novel classified self-organising map algorithm is proposed to solve the problem. First, according to the K-means algorithm, targets are classified into groups that are determined by the number of AUVs. Second, according to the self-organising map algorithm, AUVs are matched with groups. Third, each AUV is provided with the accessible order of the targets in the group. The novel classified self-organising map algorithm can be used not only to reduce the total energy consumption in a multi-AUV system, but also to give the most efficient accessible order of targets for AUVs. Results of simulations conducted to prove the applicability of the algorithm are given.

The paper presents physical modeling, design, simulations, and experimentation on a novel Soft Underwater Artificial Skin (SUAS) used as tactile sensor. The SUAS functions as an electrostatic capacitive sensor, and it is composed of a hyperelastic membrane used as external cover and oil inside it used to compensate the marine pressure. Simulation has been performed studying and modeling the behavior of the external interface of the SUAS in contact with external concentrated loads in marine environment. Experiments on the external and internal components of the SUAS have been done using two different conductive layers in oil. A first prototype has been realized using a 3D printer. The results of the paper underline how the soft materials permit better adhesion of the conductive layer to the transducers of the SUAS obtaining higher capacitance. The results here presented confirmed the first hypotheses presented in a last work and opened new ways in the large-scale underwater tactile sensor design and development. The investigations are performed in collaboration with a national Italian project named MARIS, regarding the possible extension to the underwater field of the technologies developed within the European project ROBOSKIN.