Ricerc@Sapienza

Given the huge rising interest in autonomous drone swarms to be employed in actual marine applications, the present paper explores the possibility to recover a distressed vessel by means of the other agents belonging to the swarm itself. Suitable approaches and control strategies are developed and tested to find the highest performance algorithms. Different rules are exploited to obtain a correct behaviour in terms of swarm interaction, namely collective and coordinated, and individual. An innovative feedback control strategy is adopted and demonstrated its effectiveness.

In this paper, we present a study on the use of fuzzy neural networks and their application to the prediction of times series generated by complex processes of the real-world. The new learning strategy is suited to any fuzzy inference model, especially in the case of higher-order Sugeno-type fuzzy rules. The data considered herein are real-world cases concerning chaotic benchmarks as well as environmental time series.