Swing-up control of underactuated planar robot aapdubot

This paper proposes the energy based controller incorporated with fuzzy neural network compensation (ECFNNC), which is used to swing up the Aapdubot and rise it to its uppermost unstable equilibrium position. Firstly, for the known dynamics model of the three-link arm, the energy based controller is designed. In the energy based controller, the singularity is successfully avoided by constructing an appropriate energy evaluation function. Secondly, as for friction of Aapdubot, because of the time-varying characteristics, an accurate friction dynamics model can not be known absolutely, thus the fuzzy neural network is introduced to offset the bad effect of friction. Finally, in order to evaluate the performance of energy based controller incorporated with fuzzy neural network compensation (ECFNNC) provided by this paper, the numerical simulations are given, it is found that ECFNNC proposed in this paper has better performance.