Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Network optimization method for oblique-tip flexible needle path tracking based on deep reinforcement learning

A technology of reinforcement learning and optimization methods, applied in neural learning methods, biological neural network models, informatics, etc., can solve the problems of single puncture path and limited puncture range, and achieve the effect of avoiding data overflow and reducing tracking errors.

Pending Publication Date: 2020-04-21
HUAZHONG UNIV OF SCI & TECH +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] Generally speaking, the flexible needle path tracking methods developed at home and abroad have shortcomings such as limited puncture range or relatively single puncture path form.

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
  • Network optimization method for oblique-tip flexible needle path tracking based on deep reinforcement learning
  • Network optimization method for oblique-tip flexible needle path tracking based on deep reinforcement learning
  • Network optimization method for oblique-tip flexible needle path tracking based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] figure 1 It is a flow chart of the optimization method of the action network for path tracking of oblique-tipped flexible needles based on deep reinforcement learning in the present invention. Such as figure 1 As shown, the method includes the following steps:

[0054] 1) Construct the simulation environment on the basis of the bicycle model of the oblique tip flexible needle proposed by Webster (Webster, and J.R.."Nonholonomic Modeling of Needle Steering."The International Journal of Robotics Research 25.5-6(2006):509-525. ). The simulation environment includes: a human tissue model, a model of a flexible needle with an oblique tip, a model of a motor used to control the rotation of the flexible needle with an oblique tip, and a model of a slide rail for pushing the flexible needle with an oblique tip forward. Among them, the inclined-tipped flexible needle is connected with the rotating motor, and the rotating motor is fixed on the slider in the guide rail.

[005...

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 belongs to the field of puncture needle path tracking, and discloses a network optimization method for oblique-tip flexible needle path tracking based on deep reinforcement learning. Themethod comprises the following steps: (1) constructing a simulation environment based on a bicycle model of an oblique-tip flexible needle; (2) initializing the whole oblique-tip flexible needle model, and meanwhile, providing a pre-planned preset tracking path; (3) constructing an action network and a target action network; (4) integrally storing [s(t), a(t), s(t + 1), R(t + 1)] as one sample into an empirical pool replay variable until the replay variable is saturated; and (5) randomly taking out a plurality of samples as training samples, training the action network and the target action network, and ensuring convergence of the two networks at the same time, wherein the trained convergent action network is the obtained action network for oblique-tip flexible needle path tracking. The action network obtained through the optimization method can be used for tracking the complex three-dimensional puncture path of the flexible needle, and compared with a traditional method based on theduty ratio, the method has smaller path tracking error.

Description

technical field [0001] The invention belongs to the field of puncture needle path tracking, and more specifically relates to a network optimization method for path tracking of inclined-tip flexible needles based on deep reinforcement learning. The optimized action network can be used to realize the purpose of tracking the three-dimensional path of flexible needles. Background technique [0002] Puncture surgery is one of the most widely used operations in clinical practice. In puncture surgery, the commonly used puncture needles are mostly rigid needles, but they can only advance in a straight line, and it is difficult to effectively avoid obstacles such as blood vessels. The flexible puncture needle can advance along the curve, thereby avoiding important blood vessels and organs, reducing the damage to the human body during puncture surgery, and reducing the pain of patients. Therefore, flexible puncture needles have received extensive attention in puncture surgery in recen...

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
IPC IPC(8): G16H50/50G06T15/00G06N3/08G06N3/04
CPCG16H50/50G06T15/00G06N3/08G06N3/045
Inventor 张旭明胡捷覃瑶王拓
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products