Deep learning method for gait control of lower limb rehabilitation robot

A rehabilitation robot and gait control technology, applied in the field of rehabilitation robots, can solve the problems of reducing the rehabilitation effect of the lower limb rehabilitation robot, poor adjustment accuracy, and inability to be effectively adjusted by the user, so as to improve the rehabilitation effect, ensure stability, and reduce the computational burden. Effect

Inactive Publication Date: 2021-03-19
连云港市第二人民医院
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the gait control system of the existing lower limb rehabilitation robot that simulates the walking regularity of normal people adopts the average shape calculated by big data, which c...

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
  • Deep learning method for gait control of lower limb rehabilitation robot
  • Deep learning method for gait control of lower limb rehabilitation robot
  • Deep learning method for gait control of lower limb rehabilitation robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] see Figure 1-5 , a deep learning method for gait control of lower limb rehabilitation robots, including the following steps:

[0057] S1. Input the data about the walking patterns of various types of normal people as a layer of control basis;

[0058] S2. Input the treatment data about the rehabilitation treatment of limb dysfunction caused by nervous system diseases as a layer of data basis;

[0059] S3. Input the patient's basic parameters and pathological data as the basis of the second-tier data;

[0060] S4. Combine the first-level control basis and the first-level data basis with the second-level data basis to form the initial patient treatment gait control data as the second-level control basis;

[0061] S5. Input the data of patients treated on the lower limb rehabilitation robot as the three-layer data basis;

[0062] S6. Through the basic function of the three-tier data and the second-tier control basis, the patient's treatment gait control data is formed ...

Embodiment 2

[0075] see Figure 1-7 , where the same or corresponding components as those in Embodiment 1 use the corresponding reference numerals as in Embodiment 1, and for the sake of simplicity, only the differences from Embodiment 1 will be described below. The difference between this embodiment 2 and embodiment 1 is: please refer to Image 6 with Figure 7 , a control method for deep learning of lower limb rehabilitation robot gait control, comprising the following steps:

[0076] S1. Input the parameters of the patient to be treated into the treatment system of the lower limb rehabilitation robot, and the gait control system generates a simulated treatment plan;

[0077] S2. Control the lower limb rehabilitation robot to treat patients, and the gait control system performs deep learning on the treatment data;

[0078] S3. The gait control system after deep learning sends the learning data to the treatment system of the lower limb rehabilitation robot, and improves the simulated t...

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 deep learning and control method for gait control of a lower limb rehabilitation robot, belongs to the field of rehabilitation robots, and comprises the steps: inputting walking rule data of various types of normal persons, and taking the walking rule data as a first-layer control basis; inputting treatment data related to rehabilitation treatment of limb dysfunction caused by nervous system diseases to serve as a layer of data basis; inputting basic parameters and pathological data of the patient to serve as a two-layer data basis; continuously perfecting gait control of the lower limb rehabilitation robot by using a deep learning method, and perfecting treatment gait simulation for a patient according to different patients on the basis that a gait control systemadopts big data to calculate a gait mean value form. Therefore, the simulation progress is effectively improved, the rehabilitation efficiency of the patient is improved, and the rehabilitation quality of the patient is improved. The rehabilitation effect of the lower limb rehabilitation robot is improved.

Description

technical field [0001] The invention relates to the field of rehabilitation robots, and more specifically, to a deep learning method for gait control of lower limb rehabilitation robots. Background technique [0002] At present, the rehabilitation treatment of limb dysfunction caused by nervous system diseases mainly relies on the one-on-one training of the therapist, which is difficult to achieve high-intensity, targeted and repetitive training requirements, and the labor intensity of the therapist is high, so it is difficult to ensure the accuracy of the training. Continuity and stability, the healing effect is also affected by the level of the therapist. [0003] In recent years, the field of neurological rehabilitation has used rehabilitation robotic equipment to perform gait rehabilitation training for patients with various neurological dysfunctions. As a new type of robot, rehabilitation robot is an important branch of medical robot and a combination of industrial rob...

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): A61H3/00G06N3/08G16H20/30
CPCA61H3/00A61H2201/5007G06N3/08G16H20/30
Inventor 刘明明许海燕耿睿吕南宁王迪张浩
Owner 连云港市第二人民医院
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap