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

Data set construction method and device based on unmanned aerial vehicle instruction sequence and terminal equipment

A technology of instruction sequence and construction method, applied in the field of data set construction, can solve problems such as complex calculation, difficult debugging and optimization

Inactive Publication Date: 2019-09-06
SHENZHEN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to propose a data set construction method, device and terminal equipment based on the UAV command sequence, to solve the calculation problems caused by the use of general data when constructing the data set of the UAV command sequence in the prior art. Problems that are complex, difficult to debug and optimize

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
  • Data set construction method and device based on unmanned aerial vehicle instruction sequence and terminal equipment
  • Data set construction method and device based on unmanned aerial vehicle instruction sequence and terminal equipment
  • Data set construction method and device based on unmanned aerial vehicle instruction sequence and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Such as figure 1 As shown, Embodiment 1 of the present invention provides a method for constructing a data set based on the command sequence of the drone, including but not limited to the following steps:

[0052] S1. Obtain an instruction sequence, and divide the instruction sequence into N groups, where N is a positive integer.

[0053] In the above step S1, each time the drone flies, a set of specified instruction sequences are executed.

[0054] In a specific application, the grouping of instruction sequences can be divided according to the actual flight scene of the UAV.

[0055] S2. Obtain sensor data when the drone executes the instruction sequence described in the i-th group, i is a positive integer less than or equal to N, and the initial value of i is 1.

[0056] In the above step S2, it is assumed that during the flight process of the UAV executing the command sequence, the measurement value of the TOF distance in the sensor is collected at a collection fre...

Embodiment 2

[0084] In the embodiment of the present invention, the process of mapping out the data image in step S3 of the first embodiment is described.

[0085] Such as Figure 5 As shown, in the embodiment of the present invention, the normalized data processing in step S3 to map the sensor data into a data image of preset pixels includes:

[0086] S311. Normalize the sensor data to obtain M pieces of normalized sensor data;

[0087] In the above step S311, the normalized sensor data is in the range of [0,1], so a color image can be mapped.

[0088] Wherein, M is a positive integer.

[0089] S312. Save the M pieces of normalized sensor data as the data images of preset pixels.

[0090] Wherein, any piece of normalized sensor data corresponds to a pixel of the data image.

[0091] In one embodiment, S312 includes:

[0092] Set the same matrix as the preset pixel;

[0093] The normalized sensor data is sequentially filled into the matrix.

[0094] Taking the sensor data as TOF dat...

Embodiment 3

[0099] The embodiment of the present invention describes the process of mapping the curve image in step S3 of the first embodiment.

[0100] Such as Figure 6 As shown, in the embodiment of the present invention, the mapping of the sensor data to a curve image with time and the sensor data as variables through the neural network in step S3 includes:

[0101] S321. Acquire sensor sample data and data sample images.

[0102] Wherein, the sample image includes a curve image corresponding to the sensor sample data.

[0103] S322. Input the sensor sample data and the sample image into the neural network for training, and record training network parameters when the image output by the neural network is similar to the sample image.

[0104] S323. Repeat training the neural network according to different sensor sample data and data sample images to obtain a training network parameter set.

[0105] S324. Optimize the neural network according to the training network parameter set to ob...

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 is applicable to the technical field of data set construction methods, and provides a data set construction method and device based on an unmanned aerial vehicle instruction sequence andterminal equipment, and the method comprises the steps: S1, obtaining the instruction sequence, and dividing the instruction sequence into N groups, N being a positive integer; S2, acquiring sensor data when the unmanned aerial vehicle executes the ith group of instruction sequences, i being a positive integer smaller than or equal to N, and an initial value of i being 1; S3, mapping the sensor data into a data image of a preset pixel, or mapping into a curve image taking time and the sensor data as variables; and S4, when i is smaller than N, enabling i to be equal to i + 1, returning to S2for circulation, obtaining a data image set and / or a curve image set after circulation is finished, and constructing the data set based on the instruction sequence of the unmanned aerial vehicle. According to the invention, the general data in the sensor can be converted into visual data, so that the sensor data of the unmanned aerial vehicle can accurately feed back an actual scene, and a reasonable unmanned aerial vehicle instruction sequence is favorably constructed.

Description

technical field [0001] The present invention relates to the technical field of data set construction methods, in particular to a data set construction method, device and terminal equipment based on command sequences of drones. Background technique [0002] In the technical science of artificial intelligence, machine learning can be said to be the core method to realize artificial intelligence. Machine learning is not a single method, but a collection of many algorithms. Among them, neural network and deep learning based on neural network are one of the many algorithms of machine learning. In the machine learning of drones, sensors are usually used to perceive information and obtain data, and then directly apply the acquired data to the controller to assist in decision-making processing, such as using sensor data to train the neural network, and then using the trained neural network , to assist in the generation of effective sensor data, which can be applied to the route pla...

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): G06F16/51G06K9/62
CPCG06F16/51G06F18/214
Inventor 蒙山严方林
Owner SHENZHEN 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