Apply Adaptive Neural Network PID Controllers for a 6DOF Robotic Arm

This thesis proposes a novel controller design for a six-axes robotic arm, based on the neural network frame learning mechanism. The controller structure includes five parts. Firstly, we get the training dataset from the actual construction of the six-axis robotic arm. Secondly, the training method of the neural network is based on adaptively adjust the weight value and error between the input layer and the hidden layer. Thirdly, put the training dataset as input of the neural network to train the model. Finally, we use Lyapunov theory to guarantee the stability of the controller design for a six-axis robotic arm, and compare it with PID controller design.