IJCAS

This paper presents two adaptive neural-fuzzy controllers equipped with compensatory fuzzy control in order to adjust membership functions, and as well to optimize the adaptive reasoning by using a compensatory learning algorithm. To the first controller is applied compensatory neural-fuzzy inference (CNFI) and to the second compensatory adaptive neural fuzzy inference system (CANFIS). Each controller is incorporated into a two channel bilateral teleoperation architecture involving force-position scheme, which combines the position control of the slave system with force reflection on the master. An analysis of stability and transparency based on a passivity framework is carried out. The resulting controllers are implemented on a one degree of freedom teleoperation system actuated by DC motors. The experimental results obtained show a fairly high accuracy in terms of position and force tracking, under free space motion and hard contact motion, what highlights the effectiveness of the proposed controllers."

Keywords: Compensatory fuzzy, neural-fuzzy, adaptive control, teleoperation, stability, transparence.