Humanoid robot stable control method of RBF-Q learning frame

A stable control method and RBF network technology, applied in the direction of adaptive control, general control system, control/regulation system, etc., can solve the problems of high instability, system nonlinearity, difficult to accurately model, etc., to achieve a good general The effect of the ability

Active Publication Date: 2015-09-23
SOUTH CHINA UNIV OF TECH
View PDF7 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The control problem of biped walking of humanoid robot is highly unstable and the system is nonlinear, so it is difficult to obtain a perfect solution through accurate modeling

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
  • Humanoid robot stable control method of RBF-Q learning frame
  • Humanoid robot stable control method of RBF-Q learning frame
  • Humanoid robot stable control method of RBF-Q learning frame

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0081] The specific implementation of the present invention will be described in detail below in conjunction with the accompanying drawings, but the implementation and protection of the present invention are not limited thereto. Achieved with technology.

[0082] (1) Through the ZMP analysis of the simplified humanoid robot model using the 3D inverted pendulum model, the center of mass and foothold trajectory of the robot during walking are calculated. Using the trajectory of the robot's center of mass and foothold, through inverse kinematics analysis, we obtain the motion trajectory of each joint during the walking process of the humanoid robot, and save it as the basic gait information of the robot offline.

[0083] (2) Design of Q-learning framework (RBF-Q Learning) based on RBF network.

[0084] 1) Q function of RBF network fitting

[0085] Combined with RBF network to approximate and fit the Q function in Q learning. Assuming that the Q function receives a state vector...

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 humanoid robot stable control method of an RBF-Q learning frame. The method comprises the following steps: the RBF-Q learning frame which solves the problems of state space serialization and behavior space serialization in a Q learning process is brought forward; an online motion adjusting stable control algorithm of the RBF-Q learning is brought forward, loci of the hip joint, the knee joint and the ankle joint of a support leg are generated, and a humanoid robot is controlled to walk stably through calculation of angles of other joints; and finally, the feasibility and validity of an RBF-Q learning frame method are verified on the Vitruvian Man humanoid robot platform designed by the laboratory. The method provided by the invention can generate a stable walking gait of the humanoid robot in an online learning process.

Description

technical field [0001] The invention relates to the field of walking stability control of a humanoid robot, in particular to an RBF network-based Q learning framework (RBF-Q Learning) stability control method for a humanoid robot. Background technique [0002] The essence of biped walking control research on humanoid robot platform is to solve a complex control problem. The solution to complex control problems is generally by modeling the entire system and solving the system equations. However, in reality, we often encounter such problems, that is, the problem itself is difficult to be accurately described by the model, or the parameters that the system depends on are too numerous and complex, so that it is difficult to solve the system equation. At this time, the problem can be solved by learning rather than elaborate modeling. [0003] The bipedal walking control problem of humanoid robot has the characteristics of high instability and nonlinear system, so it is difficul...

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): G05B13/04
Inventor 毕盛黄铨雍韦如明闵华清董敏
Owner SOUTH CHINA UNIV OF TECH
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