Control method for simulating ball control of soccer robot

A football robot and control method technology, applied in the field of machine learning and intelligent body control, to achieve the effect of increasing the score and winning rate

Inactive Publication Date: 2018-09-21
NANJING UNIV OF POSTS & TELECOMM
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

One disadvantage of the off-strategy is that when learning the optimal strategy, any action will be executed...

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
  • Control method for simulating ball control of soccer robot
  • Control method for simulating ball control of soccer robot
  • Control method for simulating ball control of soccer robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0043] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It should also be understood that terms such as those defined in commonly used dictionaries should be understood to have a meaning consistent with the meaning in the context of the prior art, and will not be interpreted in an idealized or overly formal sense unless defined as herein Explanation.

[0044] In the policy learning agent is about to execute the value of the policy, including the number of exploration steps, so that the performance can be improved iteratively. Therefore, in the present invention, the agent learns and explores using the Sarsa (λ) algorithm to learn. First, the n...

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 control method for simulating ball control of a soccer robot. According to the method, the dimensionalities of a state space are reduced with a tile coding linear function approximation method; a soccer robot agent module selects a Sarsa (lambda) algorithm in reinforcement learning so as to score strategies online; an optimal strategy can be selected by means of trainingand on the basis of a principle of high score first; and simulation results show that the Sarsa (lambda) algorithm can greatly improve a ball control rate. According to the method of the invention, the reinforcement learning is applied on the basis of the Sarsa (lambda) algorithm. With the method adopted, in a keepaway test, a player can control a ball for a long time and achieves a high ball-holding rate, and therefore, the ball can be transferred cooperatively among a plurality of agents, or the agents can find suitable opportunities to shoot the ball, and therefore, scores can be gained, and a win rate can be improved.

Description

technical field [0001] The invention relates to a control method for a simulated robot, in particular to a control method for a simulated soccer robot, and belongs to the technical fields of machine learning and intelligent body control. Background technique [0002] Reinforcement learning can be regarded as a trial and evaluation process. In the process of interacting with the environment, the agent chooses an action to act on the environment. After the environment executes the action, the state changes, and at the same time, a reinforcement signal (reward or punishment) is generated to feed back to the agent. . The agent chooses the next action according to the reinforcement signal and the current state of the environment. The principle of selection is to increase the probability of receiving positive reinforcement (usually represented by Q value in the program). The basic principle is as follows: figure 1 shown. [0003] Such as figure 1 As shown, when the agent intera...

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
IPC IPC(8): G05B13/02G05B13/04G05B17/02
CPCG05B13/0265G05B13/042G05B17/02
Inventor 粱志伟胡丽娟
Owner NANJING UNIV OF POSTS & TELECOMM
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