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

Surgical instrument clamping force sensing method based on deep learning

A surgical instrument and deep learning technology, applied in the field of medical robots, can solve the problems of inability to accurately obtain the clamping force of surgical instruments and low precision, and achieve the effect of improving perception accuracy and improving acquisition accuracy.

Active Publication Date: 2021-02-02
HARBIN INST OF TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the existing minimally invasive surgical robot system cannot accurately obtain the clamping force of surgical instruments and has low precision, the present invention proposes a method for sensing the clamping force of surgical instruments based on deep learning

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
  • Surgical instrument clamping force sensing method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0018] Specific implementation mode one: combine figure 1 Describe this embodiment, the deep learning-based surgical instrument clamping force perception method described in this embodiment, its specific method is as follows:

[0019] Step 1. Use the motor position θ and motor speed collected from the minimally invasive surgical robot system motor speed symbol Absolute value of motor speed Motor current I, motor current symbol sgn(I), motor current absolute value abs(I t ) to construct the input data matrix M;

[0020] Step 2. Input the data input matrix M into the convolutional network layer, input the output result into the attention mechanism module, further input the output result into the average pooling layer, and then input the output result into the global average pooling layer;

[0021] Step 3. Data splicing of the motor current, motor current sign, and absolute value of the motor current in the input data matrix M and the output result of the global average po...

specific Embodiment approach 2

[0024] Specific implementation mode two: combination figure 1 Describe this embodiment. This embodiment is a further limitation of the clamping force sensing method described in the first specific embodiment. In the deep learning-based surgical instrument clamping force sensing method described in this embodiment, in the first step data matrix Among them, sgn( ) means to take symbolic operation, abs( ) means to take absolute value calculation, the subscript t means the data of the current sampling period, and t-1 means the data of the previous sampling period;

[0025] In this specific embodiment, using the motor position θ, the motor speed motor speed symbol Absolute value of motor speed Motor current I, motor current symbol sgn(I), motor current absolute value abs(I t ) constructs a data matrix M to provide a rich and accurate data source for clamping force perception, thereby solving the shortcomings of high cost and poor accuracy of the existing minimally invasive ...

specific Embodiment approach 3

[0026] Specific implementation mode three: combination figure 1 Describe this embodiment. This embodiment is a further limitation of the clamping force sensing method described in the first specific embodiment. In the deep learning-based surgical instrument clamping force sensing method described in this embodiment, in the second step The convolution kernel size of the convolutional network layer is 3×3, the number of convolution kernels is 128, the convolution step is 1, and the activation function is ReLu;

[0027] In this specific embodiment, the size of the convolution kernel of the convolutional network layer in step 2 is 3×3, the number of convolution kernels is 128, the convolution step is 1, and the activation function is ReLu, which can be implemented in minimally invasive surgery. Accurately obtain the holding force of surgical instruments in the robot system to improve the accuracy of acquisition.

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 surgical instrument clamping force sensing method based on deep learning, and relates to the field of medical robots. The method aims to solve the problems that an existing minimally invasive surgery robot system cannot accurately obtain the clamping force of a surgical instrument and is low in precision. During application, the clamping force can be sensed only by acquiring the current of an existing motor, the angular position of a driving motor and the angular speed of the driving motor of the surgical robot system, extra hardware cost is avoided, and high-temperature disinfection is not affected; Based on a convolutional neural network, the surgical instrument clamping force sensing model is constructed in combination with the attention mechanism module and the feedback of the current of the driving motor, and compared with an existing model, the clamping force sensing precision is improved, so that the surgical instrument clamping force is accurately obtained in a minimally invasive surgical robot system, and the obtaining precision is improved. The invention is applicable to the field of medical robots.

Description

technical field [0001] The invention relates to the field of medical robots, in particular to a method for sensing clamping force of surgical instruments based on deep learning. Background technique [0002] In recent years, the application of endoscopic minimally invasive surgical robots has improved the surgical effect and reduced the pain of patients. The doctor controls the slender surgical instruments protruding into the patient's cavity through the master operator to achieve various surgical operations. However, the current minimally invasive surgical robot system lacks the perception of clamping force during the operation, which greatly reduces the doctor's surgical presence, increases the difficulty and time of the operation, and cannot effectively meet the intuitive needs of minimally invasive surgery. [0003] The clamping force sensing schemes of surgical instruments that are still in the laboratory research stage mainly include the following categories: integrat...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06N3/045G06F2218/00
Inventor 潘博郭勇辰刘柏男付宜利
Owner HARBIN INST OF 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com