L. Behera et al., NEURO-ADAPTIVE HYBRID CONTROLLER FOR ROBOT-MANIPULATOR TRACKING CONTROL, IEE proceedings. Control theory and applications, 143(3), 1996, pp. 270-275
The paper is concerned with the design of a hybrid controller structur
e, consisting of the adaptive control law and a neural-network-based ]
earning scheme for adaptation of time-varying controller parameters. T
he target error vector for weight adaptation of the neural networks is
derived using the Lyapunov-function approach. The global stability of
the closed-loop feedback system is guaranteed, provided the structure
of the robot-manipulator dynamics model is exact. Generalisation of t
he controller over the desired trajectory space has been established u
sing an online weight-learning scheme. Model learning, using a priori
knowledge of a robot arm model, has been shown to improve tracking acc
uracy. The proposed control scheme has been implemented using both MLN
and RBF networks. Faster convergence, better generalisation and super
ior tracking accuracy have been achieved in the case of the RBF networ
k.