Collaborative robot assisted smart needle placement

Abstract Needles are key tools to realize minimally invasive interventions. Physicians commonly rely on subjectively perceived insertion forces at the distal end of needle when advancing tip desired target. However, detecting tissue transitions is difficult since sensed dominated by shaft forces. Disentangling has potential substantially improve placement accuracy.We propose a collaborative system for robotic insertion, relaying haptic information directly physician feedback through light weight robot. We integrate optical fibers into medical needles and use coherence tomography image moving surface needle. Using convolutional neural network, we estimate acting from data. feed back estimated real time robot control. When inserting constant velocity, force change penetrating layers up 94% between deep compared handle 2.36 %. Collaborative results in more sensible with (49.79 ± 25.51)% conventional (15.17 15.92) Tissue prominent utilizing shaft, indicating that informed advancement possible our system.