VSE knjižnice (vzajemna bibliografsko-kataložna baza podatkov COBIB.SI)
  • Uncalibrated visual servo control for 2 DOF parallel manipulator with neural network [Elektronski vir]
    Klobučar, Rok ; Pačnik, Gregor ; Šafarič, Riko
    In this paper, a mu1tilayer feedforward network is applied to the robot visual servo control problem. The network is trained with an end effector position. After training, performance is measured by ... having the network generate joint angles for arbitrary end effector trajectories. A 2-degrees-of-freedom (DOF) parallel manipulator is used for the study. It is found that neural networks provide a simple and effective way to control the robot tasks. This paper explores the application of a neural network for approximating the nonlinear transformation relating the robot's tip position from the image coordinates to its joint coordinates. Computer simulation examples are given to illustrate the significance of this method.
    Vir: Conference proceedings [Elektronski vir] (Str. 241-246)
    Vrsta gradiva - prispevek na konferenci
    Leto - 2007
    Jezik - angleški
    COBISS.SI-ID - 11380502

Vnos na polico