A Realization Method of Humanoid Robot Adaptive Walking Framework Based on CPG Model

A technology of a humanoid robot and its implementation method, which is applied in the direction of manipulators, program-controlled manipulators, manufacturing tools, etc., can solve the problems of insufficient stability and adaptability, and achieve the effect of improving adaptability

Active Publication Date: 2021-03-02
CENT SOUTH UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of insufficient stability and adaptability in the existing CPG-based humanoid robot control

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
  • A Realization Method of Humanoid Robot Adaptive Walking Framework Based on CPG Model
  • A Realization Method of Humanoid Robot Adaptive Walking Framework Based on CPG Model
  • A Realization Method of Humanoid Robot Adaptive Walking Framework Based on CPG Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0046] The present invention proposes a method for realizing an adaptive walking frame of a humanoid robot based on a CPG model. The whole frame diagram is attached figure 1 shown, including the following steps:

[0047] Step 1: Flat ground is the easiest environment for humanoid robots to walk, so a relatively simple CPG network can be designed to achieve flat ground walking, which provides a basis for the subsequent realization of more complex adaptive walking. The rhythm signal output by CPG is converted and used as the torso trajectory of the humanoid robot end effector foot and torso, so the constructed CPG network can use fewer neurons. Humanoid robot end effector foot and torso as attached figure 2 shown. In this step, the CPG contains only two neurons. The mathematical expression for each neuron is:

[0048]

[0049]

[0050] y i =...

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 realizing an adaptive walking frame of a humanoid robot based on a central pattern generator (Central Pattern Generator, CPG) model. The invention first designs the CPG network to output reasonable rhythm control signals, so that the humanoid robot can walk on flat ground. Then, a neural network-based learning module is designed, which can learn to output the desired rhythm compensation signal to act on the output of the original CPG. Finally, a reasonable robot feedback is designed so that the entire control framework can output the desired rhythmic control signal according to the environment to adapt to various slope environments. The invention solves the problem that the CPG model is difficult to generate accurate and diverse rhythm signals in the field of robot bionic control, improves the practicability of the CPG model in the field of robot control, and has great significance for designing a more adaptive humanoid robot system.

Description

technical field [0001] The invention belongs to the field of robot bionic control, in particular to a method for realizing an adaptive walking frame of a humanoid robot based on a CPG model. Background technique [0002] The movement of robots in unknown and unstructured environments has always been one of the research difficulties in the field of humanoid robot control. As a high-degree-of-freedom dynamic system, the motion control of a humanoid robot not only needs to consider the coordination among multiple joints, but also needs to process the feedback information interacting with the environment in real time. At present, the model-based method is a typical method to control the motion of humanoid robots. However, its shortcomings are also obvious. The effectiveness of this method is based on the accurate modeling of the humanoid robot body and its environment. Therefore, The workload of measurement and calculation is large, and it is difficult to compensate for the mod...

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): B25J9/16
CPCB25J9/163
Inventor 王勇薛喜辉陈白帆
Owner CENT SOUTH UNIV
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