A learning-based tip contact force estimation method for tendon-driven continuum manipulator

Abstract

Although tendon-driven continuum manipulators have been extensively researched, how to realize tip contact force sensing in a more general and efficient way without increasing the diameter is still a challenge. Rather than use a complex modeling approach, this paper proposes a general tip contact force-sensing method based on a recurrent neural network that takes the tendons’ position and tension as the input of a recurrent neural network and the tip contact force of the continuum manipulator as the output and fits this static model by means of machine learning so that it may be used as a real-time contact force estimator. We also designed and built a corresponding three-degree-of-freedom contact force data acquisition platform based on the structure of a continuum manipulator designed in our previous studies. After obtaining training data, we built and compared the performances of a multi-layer perceptron-based contact force estimator as a baseline and three typical recurrent neural network-based contact force estimators through TensorFlow framework to verify the feasibility of this method. We also proposed a manually decoupled sub-estimators algorithm and evaluated the advantages and disadvantages of those two methods.

Safety enhanced surgical robot for flexible ureteroscopy based on force feedback

“…We here use simple subtraction to represent this deviation and then display it to the operator. For axial force and torque, this representation is approximately linear because the interactive force and torque can be regarded as directly superimposed on the joint sensor; for bending torque, due to the special cable‐driven structure of the flexible ureteroscope, the interactive force will be reflected in the knob's torque in a nonlinear way 24 when it's bending.…”

“…Sensing interactive forces is usually the first step for force feedback. Although a miniature fibre sensor 23 for bending torque, due to the special cable-driven structure of the flexible ureteroscope, the interactive force will be reflected in the knob's torque in a nonlinear way 24 when it's bending.…”

Stochastic model-based contact force estimation for concentric tube robots

“…It employed FBG sensors and an extended Kalman filter to realize the real-time shape and force sensing. A recurrent neural network has been used in [24] to provide a real-time tip contact force estimator for a tendon-driven continuum manipulator. In [10], a data-driven approach based on Deep Direct Cascade Learning has been proposed to create a force-from-shape sensor and estimate CTRs' tip contact force in the 3D workspace through backbone deflection.…”

Koopman Operator-based Extended Kalman Filter for Cosserat Rod Wrench Estimation

“…An alternative approach is to turn the continuum robot itself into a force/moment sensor, which is known as intrinsic force/wrench sensing [3], [5], [9], [10]. Such algorithms generally require a model for the continuum/soft robot, which can be either physical-based [6], [11]- [13] or data-driven [14]- [16].…”