Functional Machine with Takagi-Sugeno Inference to Coordinated Movement in Underwater Vehicle-Manipulator Systems

This paper investigates the viability of applying a functional machine with a fuzzy approach for redundancy resolution to an autonomous underwater vehicle-manipulator system (UVMS). The functional machine is constructed by a linear combination of sigmoidal functions, with a topology similar to the perceptron, and its inference is developed by fuzzy logic. The proposed algorithm generates a desired trajectory for the vehicle that takes into account two control objectives: the energy savings and the increase of system manipulability by a smooth actuation. The computer simulation results demonstrate the efficiency of this approach.