Formalized inference method of autonomous unmanned aerial vehicle on the basis of weighted fuzzy Petri net

A reasoning method and UAV technology, which can be used in electrical digital data processing, design optimization/simulation, special data processing applications, etc., and can solve problems such as poor practicability

Active Publication Date: 2016-10-26
NORTHWESTERN POLYTECHNICAL UNIV
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of poor practicability of the existing formal reasoning method based on fuzzy

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
  • Formalized inference method of autonomous unmanned aerial vehicle on the basis of weighted fuzzy Petri net
  • Formalized inference method of autonomous unmanned aerial vehicle on the basis of weighted fuzzy Petri net
  • Formalized inference method of autonomous unmanned aerial vehicle on the basis of weighted fuzzy Petri net

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] refer to Figure 1-4 . The present invention is based on weighted fuzzy Petri net autonomous unmanned aerial vehicle formal reasoning method concrete steps are as follows:

[0066] Step 1. Define WFPN as a 10-tuple:

[0067] WFPN=(P, T, D, I, O, α, β, f, Th, W)

[0068] in:

[0069] P={P 1 , P 2 , P 3 ,...,P m} is the place set, including the premise and conclusion of the rule, it is a collection of finite places;

[0070] T={t 1 , t 2 , t 3 ,...,t n} is a transition set, which is a set of finite transitions, and its corresponding rule confidence vector CF=(μ 1 , μ 2 , μ 3 ,..., μ n );

[0071] D = {d 1 , d 2 , d 3 ,...,d m} is a set of finite propositions, |P|=|D|;

[0072] I: is the input matrix. I=[δ ij ] m×n (δ ij ∈[0,1], i=1,2,...,m; j=1,2,...,n) means p i to t j input relationship and weight, when p i is t j δ ij =w ij , otherwise 0;

[0073] O: is the output matrix, O=[γ ij ] m×n ( ij ∈[0,1], i=1,2,...,m; j=1,2,...,n means t j ...

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 formalized inference method of an autonomous unmanned aerial vehicle on the basis of a weighted fuzzy Petri net, and is used for solving the technical problem of poor practicality of a traditional formalized inference method based on a fuzzy Petri net. The technical scheme of the formalized inference method is that the formalized inference algorithm of the weighted fuzzy Petri net is introduced, the corresponding column element and the corresponding row element of a matrix are multiplied in the inference algorithm, and a maximum value operator is taken to replace a summation operator obtained in a way that the corresponding column element and the corresponding row element of the matrix are multiplied in the background prior so as to adapt to a situation that the output propositions of a plurality of rules are the same in the formalized inference strategy rule set of the autonomous unmanned aerial vehicle. Since the intelligent decision formalized inference method on the basis of the weighted fuzzy Petri net is adopted, the autonomous unmanned aerial vehicle can effectively adapt to the situation that a formalized inference process strategy rule set simultaneously has different input propositions to bring different contributions and influences on a rule conclusion and the output propositions of the plurality of rules are the same when the autonomous unmanned aerial vehicle executes a double-aerial-vehicle or multi-aerial-vehicle search/attack task, and practicality is high.

Description

technical field [0001] The invention relates to a formal reasoning method based on fuzzy Petri net, in particular to a formal reasoning method for autonomous drone based on weighted fuzzy Petri net. Background technique [0002] Autonomous reasoning and decision-making is an important feature of highly autonomous, intelligent, and collaborative UAVs. Through formal reasoning technology, drones can execute automated reasoning and decision-making based on rules, which is of great significance for improving the autonomy, intelligence and collaboration of drones. The existing formal reasoning methods are: the formal reasoning method based on fuzzy Petri net. [0003] The document "Research on PAAIS Knowledge Processing Based on Fuzzy Petri Nets, Master's Degree Thesis, Northwestern Polytechnical University, 2006, p27-30" discloses a formal reasoning method based on fuzzy Petri nets. This method is used for beyond visual range attack operations. Firstly, the fuzzy rule base for...

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): G06F17/50
CPCG06F30/22
Inventor 谭雁英周军童明祝小平杨俊鹏赵斌
Owner NORTHWESTERN POLYTECHNICAL 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