This paper is devoted to solve the positioning control problem of underactuated robot manipulator. Artificial Neural Networks\r\nInversion technique was used where a network represents the forward dynamics of the system trained to learn the position of the\r\npassive joint over the working space of a 2R underactuated robot. The obtained weights from the learning process were fixed, and\r\nthe network was inverted to represent the inverse dynamics of the system and then used in the estimation phase to estimate the\r\nposition of the passive joint for a new set of data the network was not previously trained for. Data used in this research are recorded\r\nexperimentally from sensors fixed on the robot joints in order to overcome whichever uncertainties presence in the real world such\r\nas ill-defined linkage parameters, links flexibility, and backlashes in gear trains. Results were verified experimentally to show the\r\nsuccess of the proposed control strategy.
Loading....