Record number :
Title of article :
Adaptive neural network tracking control for manipulators with uncertain kinematics, dynamics and actuator model
Author/Authors :
Cheng، نويسنده , , Long-Yu Hou، نويسنده , , Zeng-Guang and Tan، نويسنده , , Min، نويسنده ,
Issue Information :
روزنامه با شماره پیاپی سال 2009
Pages :
From page :
To page :
Abstract :
A neural-network-based adaptive controller is proposed for the tracking problem of manipulators with uncertain kinematics, dynamics and actuator model. The adaptive Jacobian scheme is used to estimate the unknown kinematics parameters. Uncertainties in the manipulator dynamics and actuator model are compensated by three-layer neural networks. External disturbances and approximation errors are counteracted by robust signals. The actuator controller is designed based on the backstepping scheme. Compared with the existing work, the proposed method considers the manipulator kinematics uncertainty, does not need the “linearity-in-parameters” assumption for the uncertain terms in the dynamics of manipulator and actuator, and guarantees the tracking error to be as small as desired. Finally, the performance of the proposed approach is illustrated by the simulation example.
Keywords :
MANIPULATORS , Tracking , uncertainty , NEURAL NETWORKS
Journal title :
Journal title :
Serial Year :
Link To Document :