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

An unmanned aerial vehicle flight state prediction method and system based on LSTM

A technology of flight status and drones, which is applied in neural learning methods, neural architectures, biological neural network models, etc., and can solve problems such as inability to predict actions with data

Active Publication Date: 2018-12-18
NORTHEASTERN UNIV
View PDF5 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] According to the above-mentioned technical problem that the existing control model cannot predict the actions occurring during the flight according to the collected flight state data, a method and system for predicting the flight state of unmanned aerial vehicle based on LSTM are provided

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
  • An unmanned aerial vehicle flight state prediction method and system based on LSTM
  • An unmanned aerial vehicle flight state prediction method and system based on LSTM
  • An unmanned aerial vehicle flight state prediction method and system based on LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] like figure 1 As shown, the present invention provides a kind of LSTM-based UAV flight action prediction method, comprising the following steps:

[0079] Step 1: Build an action tag dictionary for converting values ​​into action tags;

[0080] Step 2: According to the same time interval, respectively collect the flight status information of the drone corresponding to multiple moments during the flight process of the drone, and the action data of the next moment corresponding to each moment; convert the action data into action label;

[0081] Step 3: For each type of UAV flight status information collected, preprocessing is performed according to the ascending order of the data values ​​of the UAV flight status information, including filling in missing value position data and replacing outlier data;

[0082] Step 4: Perform one-hot encoding on the action label, and form a data set in the form of a data matrix together with the preprocessed UAV flight status information...

Embodiment 2

[0151] The present invention also provides an LSTM-based UAV flight action prediction system, comprising:

[0152] Action tag dictionary unit: used to convert values ​​into action tags;

[0153] Data acquisition unit: used to collect the flight state information of the drone corresponding to multiple moments during the flight process of the drone and the action data of the next moment corresponding to each moment when building the model, and pass the action data through the action tag dictionary unit into action tags;

[0154] Or it is used to collect the UAV flight status information of the UAV at the current moment that needs to be predicted;

[0155] Data preprocessing unit: for each type of UAV flight status information collected by the data acquisition unit, preprocessing is performed according to the ascending order of the data values ​​of the UAV flight status information, including filling missing value position data and replacing outlier points data;

[0156] Model...

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 unmanned aerial vehicle flight state prediction method and system based on LSTM. The method of the invention comprises the following steps: step 1, constructing an action label dictionary; 2, collecting flight state information and motion data of the unmanned aerial vehicle; 3, preprocessing the collected flight state information of each unmanned aerial vehicle; 4, forming a data set in the form of a data matrix; 5, randomly dividing the data set into 70 percent of the training set and 30 percent of the verification set; obtaining the improved LSTM model of a long-short-term memory network with variance by training. 6, tuning the super parameters of the model to obtain a final model by using a verification set; 7: collecting the UAV flight state information of theUAV at the current time which needs to be predicted, and inputting the information into the final model after preprocessing and filtering to obtain the UAV flight motion prediction result. The technical proposal of the invention solves the problem that the existing control model cannot predict the flight action according to the collected flight state data.

Description

technical field [0001] The present invention relates to the technical field of UAV flight control, in particular, to a method and system for predicting the flight state of UAV based on LSTM. Background technique [0002] More than ten years ago, in the early stage of the development of drones, people were more concerned about how to make drones fly stably, faster, and higher. However, with the development of chips, artificial intelligence, and big data technologies, , UAVs have begun to enter the development trend of intelligence, terminalization, and clustering. UAVs have flown from military applications far away from people's vision into ordinary people's homes, allowing laymen to learn for a short time, and can also enjoy stable and reliable flight entertainment. Among them, it is undeniable that the development of flight control technology is the biggest driver of UAV changes in this decade. The flight control of UAVs is one of the main problems in the research field of...

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): G06N3/04G06N3/08
CPCG06N3/049G06N3/08
Inventor 高庆龙王骄王中岩潘家鑫刘英楠迟森
Owner NORTHEASTERN UNIV
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