Formation tracking and transformation control of nonholonomic AUVs based on improved SOM method

Abstract

Formation tracking and transformation are the key problems in formation control of multi-AUV (autonomous underwater vehicle) system. In this paper, an improved self-organizing map (SOM) neural network method is proposed for solving the formation issues of a group of autonomous underwater vehicles (AUVs). All the AUVs in the formation are treated equal to be the leaders or the followers. The desired locations are set as input vectors of SOM neural network. Self-organizing competitive calculations are carried out with workload balance taken into account. Output vectors of the SOM network are the corresponding AUVs' coordinates, so that a group of AUVs are controlled to reach the designated locations. This method hold the followers' positions in the formation when the formation moves as a whole along pre-planned trajectories. Moreover, the formation could change its shape as needed in the procedure. Formation transformations are efficient and reasonable using this strategy. Finally, due to the characteristics of SOM neural network, adaption and fault tolerance can be achieved. Simulation results demonstrate the effectiveness of the proposed approach.