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

Autonomous learning and evolution method of brain-myoelectric fusion perception for extremity exoskeleton-assisted rehabilitation

A self-learning and exoskeleton technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as the lack of brain-myoelectric fusion exoskeletons

Active Publication Date: 2022-05-20
XI AN JIAOTONG UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a limb exoskeleton-assisted rehabilitation brain-myoelectric fusion perception autonomous learning and evolution method, which solves the shortcomings and practical problems of the existing brain-myoelectric fusion exoskeleton

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
  • Autonomous learning and evolution method of brain-myoelectric fusion perception for extremity exoskeleton-assisted rehabilitation
  • Autonomous learning and evolution method of brain-myoelectric fusion perception for extremity exoskeleton-assisted rehabilitation
  • Autonomous learning and evolution method of brain-myoelectric fusion perception for extremity exoskeleton-assisted rehabilitation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. The examples are only used to explain the present invention, not to limit the protection scope of the present invention.

[0031]Taking the control object as a power-assisted prosthetic hand (the power-assisted prosthetic hand includes the elbow, which includes a large part of the upper limb, and can be used as a representative of the power-assisted upper limb exoskeleton), and the user is a patient with spinal cord injury as an example, the present invention proposes an upper limb exoskeleton The autonomous learning and evolution method of assisted rehabilitation brain-myoelectric fusion perception solves the shortcomings of the existing brain-myoelectric fusion exoskeleton interactive execution logic, poor rehabilitation effect, and single rehabilitation function.

[0032] 1. Pre-training process

[0033] The present invention refers to figu...

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 method for autonomous learning and evolution of brain-myoelectric fusion perception assisted by extremity exoskeleton. The invention expands the brain-myoelectric fusion strategy in the time span of the rehabilitation process, and combines deep learning autonomous learning technology to fully consider The brain-myoelectric characteristic changes in the time span of the user's rehabilitation process are analyzed, and the brain-myoelectricity is integrated during the user's rehabilitation process by adaptively changing the decision-making weight of the brain-myoelectricity, so as to adaptively serve the user's rehabilitation process and daily activities. Compared with the traditional brain-myoelectric fusion exoskeleton, the present invention overcomes the bottleneck of recognition performance, serves the whole process of user rehabilitation, realizes the mutual adaptation and mutual learning between the user and the exoskeleton device, and solves the problem of the existing brain-myoelectricity fusion exoskeleton. Insufficient and practical problems of fusion exoskeleton.

Description

technical field [0001] The invention relates to the field of brain-computer interface technology and sports rehabilitation, in particular to an autonomous learning and evolution method of exoskeleton-assisted movement / rehabilitation brain-myoelectric fusion perception. Background technique [0002] Limbs play a vital role in the interaction between the body and the external environment in daily activities; healthy people can easily complete simple and complex limb movements, but patients with spinal cord injuries, strokes or physical disabilities lack or lose control of some limbs ability to function normally. Brain-controlled exoskeletons can assist disabled patients to perform actions necessary for daily activities. However, the recognition of EEG signals for the action intention of disabled patients has always faced the problems of low accuracy, poor stability, and weak robustness, especially for unilateral limbs. Action manipulation, the EEG signals that distinguish dif...

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 Patents(China)
IPC IPC(8): G06N3/04G06N3/063G06N3/08
CPCG06N3/063G06N3/084G06N3/044G06N3/045
Inventor 张小栋蒋永玉陆竹风张腾张毅蒋志明
Owner XI AN JIAOTONG UNIV