Extended control of walking motion for use in an autonomous robot platform

The paper presents the design and simulation of a three degrees-of-freedom mechatronic system for use in an autonomous robotic platform. The tracking reference for the angular joints is given using a trained neuro-fuzzy model instead of the usual inverse kinematic system. The joint actuators are driven using a selection of position controllers featuring PID control, simple and enhanced extenics control and a number of fuzzy controllers, some of which recently introduced. A comparison for their performance is then provided. The paper draws on some previously investigated concepts of great actuality to the field such as neuro-fuzzy networks, extenics and reduced-base fuzzy control.