Trajectory Tracking Controller Design for Percutaneous Interventional Procedures

Abstract

The aim of this research work is to implement a trajectory tracking controller for a flexible needle within a tissue region, using a neural network-based approach. Initially, a kinematic model for steerable needle inside the tissue domain is considered based on a unicycle model while considering nonholonomic constraints. Subsequently, a neural network (NN) architecture based closed loop control strategy is implemented to track a desired trajectory on a specified plane. The efficacy of the developed controller is confirmed through simulation studies. Furthermore, a comparative study is conducted, involving a standard Proportional-Integral-Derivative (PID) controller, to demonstrate the efficacy of the proposed controller. The simulation outcomes demonstrate that the proposed control scheme outperforms the conventional PID approach.