Intelligent control of a micromanipulator actuated with shape memory alloy tendons

摘要: During the past 20 years, tremendous advancements have been made in fields of minimally invasive surgery (MIS) and robotic assisted (MIRA) surgery. The technologies associated with these their own drawbacks, however. surgical robots used MIRA procedures are large, costly, do not offer miniaturized articulation necessary to facilitate additional advancements. This research tests hypothesis that miniature actuation can overcome some limitations current systems by demonstrating accurate, repeatable control a small end-effector. A simple two link manipulator is designed fabricated, using antagonistic shape memory alloy (SMA) tendons as actuators, simulate motions Artificial neural networks (ANNs) conjunction real-time visual feedback "learn" inverse system dynamics endpoint trajectory. Experimental results presented for indirect, on-line learning control. Manipulator tip trajectories shown be accurate within 0.5 mm. These confirm SMAs effective actuators systems, intelligent accurately trajectory systems.