DESIGN, IMPLEMENTATION, AND COOPERATIVE COEVOLUTION OF AN AUTONOMOUS/TELEOPERATED CONTROL SYSTEM FOR A SERPENTINE ROBOTIC MANIPULATOR

摘要

This paper describes the design, implementation, and machine learning issues associatedrnwith developing a control system for a serpentine robotic manipulator. The purpose of therncontrol system is to provide autonomous/teleoperative control of the serpentine roboticrnmanipulator, as well as full robotic control during operation of the manipulator within anrnenclosed environment such as an underground storage tank.rnThe controller algorithms make use of both low-level joint angle control employingrnforce/position feedback constraints, and high-level coordinated control of end-effectorrnpositioning. Since the inverse kinematics solutions for a hyper-redundant serpentine manipulatorrnare extremely difficult if not impossible to obtain using standard techniques, a variety of methodsrnfrom evolutionary computation were employed to arrive at a suitable inverse kinematics modelrnfor the manipulator. Additional constraints, such as various joint angle bending restrictions, jointrnconstraints within a given stage of the manipulator, and customer requirements may be easilyrnincorporated into the machine learning process through the fitness function.rnThis approach has resulted in a system which offers both high-level full robotic controlrnand low-level telerobotic control modes, and provides a high level of dexterity for the operator.