Self-Organizing Decision-Making System for AUV

Abstract

Autonomous underwater vehicles (AUVs) have great advantages for activities in deep oceans, and are expected as the attractive tool for near future underwater development or investigation. However, AUVs have various problems which should be solved for motion control, acquisition of sensors' information, behavioral decision, navigation without collision, self-localization and so on. In order to realize the useful and practical robots which can work in the ocean, underwater vehicles should take their action by judging the changing condition from their own sensors and actuators, and are desirable to make their behaviors with limited efforts of the operators, because of the features caused by the working environment. Therefore, the AUVs should be autonomous and have adaptive function to their environment. AUVs have non-liner coupled dynamics in six degrees of freedom, and the changes of the equipments of robots have influence on the control system. In this paper, a new control system for AUVs using modular network SOM (mnSOM) proposed by Tokunaga et al. is described. The mnSOM is an extension of the conventional SOM in which each vector unit is replaced by function modules such as NN and SOM, and has both characteristic of NN (supervised learning, non-linear mapping, etc.) and SOM (interpolation, topology preservation, etc.). The proposed system has two maps (forward model map and controller map) using recurrent type NN mnSOM. A forward model map (FMM) expresses the relationship between control force and states variables, and is used to estimate a current dynamics of an AUV. A controller map (CM) expresses suitable controllers corresponding to the FMM. The efficiency of the system is investigated through the simulations and experiments.