Human motion intention recognition method of waist assistance exoskeleton robot
An exoskeleton robot and human motion technology, which is applied in the fields of appliances, sensors, medical science, etc. to help people move around, can solve the problems of difficult detection and identification of human motion intention, and achieve high reliability, low price, and easy implementation.
Pending Publication Date: 2021-02-09
宁波工业互联网研究院有限公司
View PDF4 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Recognizing human motion intentions requires the fusion of multi-sensor information for decision-making, so although waist-assisted exoskeleton robots have obvious social and economic value, due to technical factors, current waist-assisted exoskeleton robot products face difficulties in detecting and identifying human motion intentions, etc. Practical problems
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0018] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.
[0019] Such as figure 1 As shown, a human body movement intention recognition method for a waist-assisted exoskeleton robot includes the following steps:
[0020] , collect signals, and establish a signal-behavioral action database: install a back IMU (inertial navigation sensor) and a back force sensor on the top of the back of the waist-assisted exoskeleton robot, and install the left thigh IMU and the left thigh strap on the waist-assisted exoskeleton robot. The left thigh force sensor, install the right thigh IMU and the right thigh force sensor at the right thigh strap of the waist-assisted exoskeleton robot, choose 100 subjects to wear the waist-assisted exoskeleton robot, and collect each subject to bend over for 10 minutes. The signal of the back IMU and the force sensor of the back when standing upright for more than 10 times, the ...
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
Login to View More Abstract
The invention discloses a human motion intention recognition method for a waist assistance exoskeleton robot. The method is characterized by comprising the steps as follows: collecting a signal, and building a signal-behavior action database; carrying out preprocessing and category calibration on the signal; randomly extracting training samples, and inputting the training samples into a binary tree support vector machine multi-classifier for training to obtain a binary tree support vector machine model; and adopting the binary tree support vector machine model to realize current human motion intention recognition; The method has the advantages that the adopted IMU and force sensor are high in reliability and low in signal noise; a moving average filtering method is adopted, so that the implementation efficiency is high, and time-consuming complex filtering operation is not needed; compared with a traditional support vector machine, the binary tree support vector machine multi-classifier adopted by the invention can realize multi-classification, and accurately classify four motion states of stooping, standing, walking with the left leg and walking with the right leg; and the motionintention of a user is better recognized, and the auxiliary assistance problem during walking, going upstairs and downstairs and carrying of the user is solved.
Description
technical field [0001] The invention relates to the field of artificial intelligence identification and control, in particular to a method for identifying human motion intentions of a waist-assisted exoskeleton robot. Background technique [0002] As a category in the field of exoskeleton robots, waist-assisted exoskeleton robots can not only assist heavy laborers and nursing staff to increase their load-bearing capacity, relieve work fatigue, prolong working life, and improve work efficiency, but also protect the bones of heavy laborers and nursing staff. and muscles, reducing the risk of lumbar muscle strain and lumbar spine injury; in addition, the waist-assisted exoskeleton robot can also assist the elderly, providing home care solutions for the social problems of the elderly caused by the aging population, assisting the elderly to walk, Activities such as mountaineering and hiking can improve the self-care ability of the elderly. [0003] Recognizing human motion inten...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): A61B5/11A61B5/00A61H3/00
CPCA61B5/1116A61B5/7267A61B5/6802A61H3/00
Inventor 徐兆红何方剑裘焱枫郏云涛田俊许留凯张克勤
Owner 宁波工业互联网研究院有限公司