This paper presents a self-tuning method of fuzzy logic controllers. The consequence part of the fuzzy logic controller is self-tuned through the Q-learning algorithm of reinforcement learning. The off policy temporal difference algorithm is used for tuning which directly approximate the action value function which gives the maximum reward. In this way, the Q-learning algorithm is used for the continuous time environment. The approach considered is having the advantage of fuzzy logic controller in a way that it is robust under the environmental uncertainties and no expert knowledge is required to design the rule base of the fuzzy logic controller.

This paper considers the trajectory tracking control of linear inverted pendulum (IP) system. First the linearized model of IP is derived to facilitate the control design. To avoid non robust reaching phase, integral sliding mode control (ISMC) has been proposed but single variable case is tested. Linear IP is a multivariable system having angle of pendulum and position of cart are two variables to be controlled. In control design, the LQR control is designed as a nominal control to get the desired trajectory. Then discontinuous control using integral sliding mode(ISM) is introduced to get desired trajectory tracking in the presence of uncertainties. This control is robust to the model uncertainties and disturbances during entire motion of the states. The simulation results are presented to show the effectiveness of proposed control scheme. The results are compared with LQR control to show the integral sliding mode control is having better tracking performance in the presence of uncertainties.