Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Operant conditioning reflex automatic machine and application thereof in control of biomimetic autonomous learning

A technique for manipulating conditioned reflexes, automata, applied in the field of bionic automata

Inactive Publication Date: 2010-03-17
BEIJING UNIV OF TECH
View PDF2 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Patents on operant conditioning automata and their applications have not yet been seen

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
  • Operant conditioning reflex automatic machine and application thereof in control of biomimetic autonomous learning
  • Operant conditioning reflex automatic machine and application thereof in control of biomimetic autonomous learning
  • Operant conditioning reflex automatic machine and application thereof in control of biomimetic autonomous learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Embodiment one: if Figure 4 , 5, Skinner's operant conditioning pigeon experiment.

[0048] The goal of Skinner's pigeon experimental training is to make it learn the behavior of pecking the red button. It gets food when it pecks the red button (positive reinforcement), nothing when it pecks the yellow button, and an electric shock when it pecks the blue button (negative reinforcement). Experiments were carried out using the Skinner operator conditioned reflex automata model method, such as figure 1 , 2 , 3 shown.

[0049] Firstly, the simplified discrete mathematical model of the pigeon experiment is given: suppose the pigeon has three states: hungry state, half-starved state and zero-starved state. When the pigeon is in a hungry state, when it is given food, the state changes to half-starved. When the pigeon is not given food or given electric shock stimulation, the pigeon is still in a hungry state, and the output is the state of the pigeon at this time; when th...

Embodiment 2

[0077] Embodiment 2: As shown in Figures 6-7, a balance control experiment of a single-stage inverted pendulum.

[0078] The goal of inverted pendulum control is to apply a force u (control amount) to the base of the trolley, which is the set of operation symbols O, that is, u=o k , k=1, 2, ..., n o . Finally, it is guaranteed that the pole does not fall down, that is, it does not exceed a predefined vertical deviation angle range. The control experiment is carried out by using Skinner's method of manipulating the conditioned automata model, such as figure 1 , 2 , 3 shown.

[0079] An inverted pendulum can be described by the following equations of motion

[0080] θ · · = m ( m + M ) gl ( M ...

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 provides an operant conditioning reflex automatic machine model, and designs a biomimetic autonomous learning control method based on the model. Aiming at the control problem of a natural world system, the operant conditioning reflex automatic machine model which can be used for describing and imitating and is designed with the function of self-organization (including autonomous learning and self-adaption) can be designed by utilizing the biomimetic self-organizing learning method, thus effectively applying bionics and psychics to the control of a system. By using the operant conditioning reflex automatic machine model (OCM), the operation (control quantity) is firstly selected at random according to the input and the state of the current system, and the operation with high probability value is inclined to be selected due to good operation orientation. After the control is implemented, the state is observed, and the control effect is output outside; then, an orientation unit is used for evaluating the state after control, modifies the probability value of a rule collection and continuously acquires the behavior with the good operation orientation, thus being capable of conveniently selecting more excellent behavior next time; and finally, the autonomous control can be realized.

Description

technical field [0001] The invention relates to a bionic automaton (Operant Conditioning Automata, hereinafter referred to as OCM) based on the principle of operating conditioning. It uses computer technology, automatic control technology, bionics, psychology, biology, etc. to realize bionic autonomous learning control. Background technique [0002] The present invention is based on Skinner's operant conditioning theory, which is different from Pavlov's classical conditioning. Classical conditioning is a process in which conditioned stimuli elicit a response. Its formula is S→R. The response is innate. The stimulus acts as a reinforcement and is presented before the behavior. Operant conditioning is the first thing to do. It is a process in which an operant response is strengthened, and its formula is R→S. The response is acquired, and its reinforcement occurs after the behavior occurs. The purpose is to let the test subject learn the specific behavior expected by the exper...

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): G06N3/00
Inventor 阮晓钢郜园园蔡建羡陈静戴丽珍
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com