東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

The Use of Artificial Intelligence Algorithms to Improve the Safety of Unmanned Aerial Vehicles.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	The Use of Artificial Intelligence Algorithms to Improve the Safety of Unmanned Aerial Vehicles./
作者:	Waddell, Abbigail G.
面頁冊數:	1 online resource (47 pages)
附註:	Source: Masters Abstracts International, Volume: 83-02.
Contained By:	Masters Abstracts International83-02.
標題:	Artificial intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28411262click for full text (PQDT)
ISBN:	9798534600148

The Use of Artificial Intelligence Algorithms to Improve the Safety of Unmanned Aerial Vehicles.
Waddell, Abbigail G.

The Use of Artificial Intelligence Algorithms to Improve the Safety of Unmanned Aerial Vehicles. - 1 online resource (47 pages)

Source: Masters Abstracts International, Volume: 83-02.

Thesis (M.S.)--North Carolina Agricultural and Technical State University, 2021.

Includes bibliographical references

This thesis discusses the use of Artificial Intelligence (AI) algorithms in autonomous unmannedaerial vehicles (UAVs). The purpose of this research is to improve crash rates and reduce thedamage caused by bail outs when said UAV is faced with an abort situation. This document willdescribe the process of designing an autonomous control system that will be tested virtually and thedesign of the AI algorithm that will be implemented. The control system will be first implemented,trained, and tested using AirSim. It is then then further evaluated by using MATLAB to compareit with standard UAV autonomy. Standard sensors and hardware found on a small UAV such as acamera, sonar, and Global Positioning System (GPS) navigation are factored into the simulation.The AI algorithm will then be integrated and tested to determine any improvement in the crashrate. The AI will be trained with the use of the Unreal Engine to detect and avoid crashes. Aseparate AI algorithm will be implemented to detect the presence of humans on the path. Both AIalgorithms factor into the system's flight path decision. The AI will be implemented on the IntelNeural Compute Stick as a means of demonstrating the possibility of implementing a robust AIprogram on a small-scale vehicle. The AI results will be compared to the original implementationto determine the extent of the improvement in safety. The algorithm uses a combination of multipledata types in training and testing. By factoring in more than just visual data, it is hoped that theUAV will be able to make impact decisions that will reduce crash and damage rates. Both a DeepConvolution Neural Network (CNN) approach and a Convolution Neural Network with NeuralCircuit Policies (NCP) were trained on the data. The AI models were used as part of the CollisionReducing Artificially intelligent System Hierarchy (CRASH) that was developed by this research.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798534600148Subjects--Topical Terms:

516317
Artificial intelligence.
Subjects--Index Terms:

Artificial intelligenceIndex Terms--Genre/Form:

542853
Electronic books.

The Use of Artificial Intelligence Algorithms to Improve the Safety of Unmanned Aerial Vehicles.
LDR:03316nmm a2200397K 4500 001 2353992
005 20230324111128.5
006 m o d
007 cr mn ---uuuuu
008 241011s2021 xx obm 000 0 eng d
020 $a 9798534600148
035 $a (MiAaPQ)AAI28411262
035 $a AAI28411262
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Waddell, Abbigail G. $3 3694323
245 1 4 $a The Use of Artificial Intelligence Algorithms to Improve the Safety of Unmanned Aerial Vehicles.
264 0 $c 2021
300 $a 1 online resource (47 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 83-02.
500 $a Advisor: Kelly, John.
502 $a Thesis (M.S.)--North Carolina Agricultural and Technical State University, 2021.
504 $a Includes bibliographical references
520 $a This thesis discusses the use of Artificial Intelligence (AI) algorithms in autonomous unmannedaerial vehicles (UAVs). The purpose of this research is to improve crash rates and reduce thedamage caused by bail outs when said UAV is faced with an abort situation. This document willdescribe the process of designing an autonomous control system that will be tested virtually and thedesign of the AI algorithm that will be implemented. The control system will be first implemented,trained, and tested using AirSim. It is then then further evaluated by using MATLAB to compareit with standard UAV autonomy. Standard sensors and hardware found on a small UAV such as acamera, sonar, and Global Positioning System (GPS) navigation are factored into the simulation.The AI algorithm will then be integrated and tested to determine any improvement in the crashrate. The AI will be trained with the use of the Unreal Engine to detect and avoid crashes. Aseparate AI algorithm will be implemented to detect the presence of humans on the path. Both AIalgorithms factor into the system's flight path decision. The AI will be implemented on the IntelNeural Compute Stick as a means of demonstrating the possibility of implementing a robust AIprogram on a small-scale vehicle. The AI results will be compared to the original implementationto determine the extent of the improvement in safety. The algorithm uses a combination of multipledata types in training and testing. By factoring in more than just visual data, it is hoped that theUAV will be able to make impact decisions that will reduce crash and damage rates. Both a DeepConvolution Neural Network (CNN) approach and a Convolution Neural Network with NeuralCircuit Policies (NCP) were trained on the data. The AI models were used as part of the CollisionReducing Artificially intelligent System Hierarchy (CRASH) that was developed by this research.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 516317
650 4 $a Electrical engineering. $3 649834
650 4 $a Aerospace engineering. $3 1002622
650 4 $a Unmanned aerial vehicles. $3 3560267
650 4 $a Datasets. $3 3541416
650 4 $a Decision making. $3 517204
650 4 $a Sensors. $3 3549539
650 4 $a Neural networks. $3 677449
653 $a Artificial intelligence
653 $a Autonomous drone
653 $a Autonomous safety
653 $a Light weight hardware
653 $a Unmanned aerial vehicles
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0544
690 $a 0538
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a North Carolina Agricultural and Technical State University. $b Electrical Engineering. $3 3181344
773 0 $t Masters Abstracts International $g 83-02.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28411262 $z click for full text (PQDT)