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

Quadruped robot motion state clustering and autonomous decision-making method

A robot movement and quadruped robot technology, applied in the field of quadruped robot movement state clustering and autonomous decision-making, can solve problems such as the inability to realize the robot's autonomous decision-making on motion parameters, and achieve improved autonomy, reduced complexity, and optimized motion performance Effect

Active Publication Date: 2022-02-25
SHANDONG UNIV OF SCI & TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem in the prior art that the robot cannot make autonomous decisions on motion parameters, the present invention provides a quadruped robot that uses a clustering algorithm to perform cluster analysis on the motion state of the quadruped robot when it walks in a static gait. Then realize the autonomous decision-making method to improve the autonomy and terrain adaptability of quadruped robots in complex and unknown terrain environments

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
  • Quadruped robot motion state clustering and autonomous decision-making method
  • Quadruped robot motion state clustering and autonomous decision-making method
  • Quadruped robot motion state clustering and autonomous decision-making method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The research object of the present invention is a bionic quadruped robot, such as figure 1 As shown, it has twelve degrees of freedom. The quadruped bionic robot has a variety of walking gaits and can walk stably on terrains with different complexity. On complex terrain, quadruped robots generally use a static gait to effectively increase their stability. When the robot walks with a static gait, its own stability is often increased by adjusting the torso in the lateral direction. In order to make the robot have sufficient stability, a minimum stability margin is generally set in the static gait planning. Degree (S m ),like figure 2 shown. The robot increases its stability margin during walking through the movement of the torso in the lateral direction. However, if S m If the value is set larger, the amount of movement of the trunk in the lateral direction △y (see figure 2 ) increases accordingly, which in turn increases the energy consumption of the robot.

[...

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

A quadruped robot motion state clustering and autonomous decision-making method, including the following steps: (1) Record the step time series corresponding to each leg of the robot for time-domain feature extraction, and record the corresponding torso roll angle of the robot in different stable states (3) Establish a comprehensive evaluation function for the motion performance of quadruped robots; (4) According to the comprehensive evaluation function, conduct experiments on quadruped robots passing through complex terrain, and obtain the robot Relevant parameters in autonomous decision-making; (5) Realize autonomous decision-making of control parameters based on the determined relevant parameters in autonomous decision-making and real-time stepping time and torso roll angle information during the robot's movement process, and autonomously generate the current walking terrain and robot movement State-appropriate movement. This method comprehensively utilizes the step time and the current stability cluster analysis results to make independent decisions, realize the adaptability of the quadruped robot to the terrain, and ensure the real-time control.

Description

technical field [0001] The invention relates to a method for clustering and autonomous decision-making of the motion state of a quadruped bionic robot, which enables the quadruped bionic robot to cluster its own state according to its own motion state data when walking on terrain with high complexity. Class analysis, and autonomous decision-making according to the analysis results, in order to improve the terrain adaptability and autonomy of its own state, which belongs to the field of robot control. Background technique [0002] The complex terrain environment has outstanding complexity and diversity, which is the main cause of various movement difficulties and dangerous situations for quadruped robots. Accurately sensing the real-time motion state of the robot when walking on complex terrain is an important prerequisite for formulating a control strategy that conforms to the current motion state and achieving stable walking. [0003] In terms of research on the motion sta...

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): B25J9/16G06K9/62
CPCB25J9/1653B25J9/1664B25J9/1661G06F18/23G06F18/214
Inventor 张帅帅朱其刚尹燕芳刘明荣学文范永
Owner SHANDONG UNIV OF SCI & TECH