Long-time human body lower limb motion prediction method based on IPSO-BPNN

An IPSO-BPNN and motion prediction technology, applied in the field of robotics, can solve problems such as low calculation efficiency, complex model calculation, and imperfect evaluation standards, and achieve the effects of high calculation efficiency, good optimization results, and fast iterative convergence speed

Active Publication Date: 2021-05-25
北京理工大学前沿技术研究院
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006]2. The calculation of the model is complex and the calculation efficiency is low;
[0007]3. Incomplete evaluation criteria

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
  • Long-time human body lower limb motion prediction method based on IPSO-BPNN
  • Long-time human body lower limb motion prediction method based on IPSO-BPNN
  • Long-time human body lower limb motion prediction method based on IPSO-BPNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0059] A long-term human lower limb motion prediction method based on IPSO-BPNN, comprising the following steps:

[0060] S1: Preprocess the joint angle data of each lower limb joint to obtain training samples and test samples corresponding to each lower limb joint. At the same time, divide the data in each training sample and each test sample into input data and In the output data part, the lower limb joints include left hip joints, right hip joints, left knee joints, right knee joints, left ankle joints and right ankle joints.

[0061] S2: Use each lower limb joint as the current joint to perform a model training operation to obtain a BPNN joint angle prediction model...

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

According to an IPSO-BPNN-based long-time human body lower limb motion prediction method provided by the invention, the initial values of the weight and the threshold value of each node in the BPNN network are obtained based on the particle swarm optimization, and six prediction models for predicting the joint angle of each lower limb joint are obtained, so that the prediction model is higher in calculation efficiency. Iterative convergence speed of the improved particle swarm optimization (IPSO) is higher, optimization results are better, and prediction results are closer to actual observation data. In addition, the original joint angle data of each lower limb joint can be reconstructed according to the set time span, so that the prediction duration can be adjusted according to the actual prediction demand, and the system delay can be covered.

Description

technical field [0001] The invention belongs to the field of robots, and in particular relates to a long-term human lower limb motion prediction method based on IPSO-BPNN. Background technique [0002] With the development of science and technology, exoskeleton robots have shown great application prospects in military, medical, fire-fighting and anti-terrorism fields, and have become a research hotspot in the field of robotics. The special feature of the power-assisted exoskeleton robot is that the human is in the operation loop, the trajectory of the robot is actively planned by the human, and the passive assistance of the robot will inevitably make the control system lag behind the human movement. Ideally, the movement of the exoskeleton robot should be consistent with the movement trajectory of the human body moment by moment. However, due to the system delay caused by mechanical transmission, control calculation and data communication, the motion of the auxiliary robot ...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/08G06V40/20G06F18/214
Inventor 刘亚丽宋遒志金冬楠祁卓
Owner 北京理工大学前沿技术研究院
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