Unlock instant, AI-driven research and patent intelligence for your innovation.

Concentric tube robot control method based on Actor-Critic deep reinforcement learning

A technology of reinforcement learning and control methods, applied in neural learning methods, surgical robots, program-controlled manipulators, etc., can solve problems such as no joint distinction and easy bifurcation

Active Publication Date: 2021-08-13
ZHEJIANG UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since it has no obvious joint distinction and is a nonlinear system prone to bifurcation, the inverse kinematics solution of the concentric tube robot is very challenging.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Concentric tube robot control method based on Actor-Critic deep reinforcement learning
  • Concentric tube robot control method based on Actor-Critic deep reinforcement learning
  • Concentric tube robot control method based on Actor-Critic deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described below in conjunction with the accompanying drawings.

[0037] refer to Figure 1 ~ Figure 3 , a concentric tube robot control method based on Actor-Critic deep reinforcement learning, including the following steps:

[0038] 1) According to figure 1 , the kinematics model of the concentric tube robot is established by using the static balance method, and the geometric parameters and mechanical parameters of the concentric tube are set according to the stiffness requirements and stability criteria, so that the system can satisfy the stiffness dominance and avoid nonlinear bifurcation:

[0039]

[0040] Among them, L is the total length of the pre-bending part of the robot, r is the curvature product of any adjacent concentric pre-bending tubes, K is the stiffness of the concentric tubes, σ is also a quantity directly related to the geometric and mechanical parameters of the robot, and N is the composition of the concentr...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a concentric tube robot control method based on Actor-Critic deep reinforcement learning. The concentric tube robot control method comprises the following steps: 1) setting geometric parameters and mechanical parameters of a concentric tube robot, and establishing a kinematic model of the concentric tube robot; 2) preprocessing data to obtain a concentric tube curvature-position state set; 3) updating the parameters of the Actor network and the Critic network by using the concentric tube curvature-position state set; and 4) according to a final convergence model, obtaining an optimal control strategy of the concentric tube robot based on Actor-Critic deep reinforcement learning, namely the required driving quantity. Compared with the prior art, the inverse kinematics calculation method of the concentric tube robot is obtained through a deep reinforcement learning method, and finally a more accurate inverse kinematics solution is obtained.

Description

technical field [0001] The invention relates to the field of concentric tube surgical robots, in particular to a control method for concentric tube robots based on Actor-Critic deep reinforcement learning Background technique [0002] At present, with the improvement of social medical level, surgical robots with high precision and high stability are gradually involved in medicine. Compared with the manipulator with rigid joints, a concentric tube robot that can flexibly bend and reach the target position along a predetermined nonlinear path has attracted widespread attention. [0003] The concentric tube robot is nested by multiple pre-bent superelastic nickel-titanium alloy tubes, and the attitude of the robot can be changed by the rotation and expansion of the driven end tubes. The concentric tube establishes the static equilibrium equation based on the classical elastic rod model to solve the calculation of the forward kinematics, and has been able to consider friction a...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): B25J9/16G06N3/04G06N3/08A61B34/30
CPCB25J9/1607G06N3/04G06N3/08A61B34/30
Inventor 冯子俊李永强冯宇冯远静刘扬
Owner ZHEJIANG UNIV OF TECH