Neural network-based compensation control of mobile robots with partially known structure

This study proposes an inverse non-linear controller combined with an adaptive neural network proportional integral (PI) sliding mode using an on-line learning algorithm. The neural network acts as a compensator for a conventional inverse controller in order to improve the control performance when the system is affected by variations on their dynamics and kinematics. Also, the proposed controller can reduce the steady-state error of a non-linear inverse controller using the on-line adaptive technique based on Lyapunov's theory. Experimental results show that the proposed method is effective in controlling dynamic systems with unexpected large uncertainties.