國立虎尾科技大學 |

Deep Learning Techniques to Improve Autonomous Driving on Single Camera Test Bed.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Deep Learning Techniques to Improve Autonomous Driving on Single Camera Test Bed./
Author:	Kukkala, Rohith.
Description:	1 online resource (111 pages)
Notes:	Source: Masters Abstracts International, Volume: 57-05.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9780355687835

Deep Learning Techniques to Improve Autonomous Driving on Single Camera Test Bed.
Kukkala, Rohith.

Deep Learning Techniques to Improve Autonomous Driving on Single Camera Test Bed. - 1 online resource (111 pages)

Source: Masters Abstracts International, Volume: 57-05.

Thesis (M.S.)--Texas A&M University - Commerce, 2017.

Includes bibliographical references

Recent advances in machine learning (ML), known as deep neural networks (DNN) or deep learning, have greatly improved the state-of-the-art for many ML tasks, such as image classification (He, Zhang, Ren, & Sun, 2016; Krizhevsky, Sutskever, & Hinton, 2012; LeCun, Bottou, Bengio, & Haffner, 1998; Szegedy et al., 2015; Zeiler & Fergus, 2014), speech recognition (Graves, Mohamed, & Hinton, 2013; Hannun et al., 2014; Hinton et al., 2012), complex games and learning from simple reward signals (Goodfellow et al., 2014; Mnih et al., 2015; Silver et al., 2016), and many other areas as well. Neural network and ML methods have been applied to the task of autonomously controlling a vehicle with only a single camera image input to successfully navigate on the road (Bojarski et al., 2016). However, advances in deep learning are not yet applied systematically to this task. In this work I used a simulated environment in order to implement and compare several methods for controlling autonomous navigation behavior using a single standard camera input device to sense the environmental state. The simulator contained a simulated car with a camera mounted on the top to gather visual data while being operated by a human controller on a virtual driving environment. The gathered data were used to perform supervised training for building an autonomous controller to drive the same vehicle remotely over a local connection. I reproduced results from previous researchers who have used simple neural networks and other ML techniques to guide similar test vehicles using a single camera. I compared these results with more complex deep neural network controllers to see if they can improve navigation performance based on past methods on measures of speed, distance, and other performance metrics on unseen simulated road driving tasks.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355687835Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Deep Learning Techniques to Improve Autonomous Driving on Single Camera Test Bed.
LDR:03006ntm a2200337K 4500 001 912192
005 20180608102941.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355687835
035 $a (MiAaPQ)AAI10689991
035 $a (MiAaPQ)tamucommerce:10663
035 $a AAI10689991
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Kukkala, Rohith. $3 1184440
245 1 0 $a Deep Learning Techniques to Improve Autonomous Driving on Single Camera Test Bed.
264 0 $c 2017
300 $a 1 online resource (111 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: 57-05.
500 $a Adviser: Derek Harter.
502 $a Thesis (M.S.)--Texas A&M University - Commerce, 2017.
504 $a Includes bibliographical references
520 $a Recent advances in machine learning (ML), known as deep neural networks (DNN) or deep learning, have greatly improved the state-of-the-art for many ML tasks, such as image classification (He, Zhang, Ren, & Sun, 2016; Krizhevsky, Sutskever, & Hinton, 2012; LeCun, Bottou, Bengio, & Haffner, 1998; Szegedy et al., 2015; Zeiler & Fergus, 2014), speech recognition (Graves, Mohamed, & Hinton, 2013; Hannun et al., 2014; Hinton et al., 2012), complex games and learning from simple reward signals (Goodfellow et al., 2014; Mnih et al., 2015; Silver et al., 2016), and many other areas as well. Neural network and ML methods have been applied to the task of autonomously controlling a vehicle with only a single camera image input to successfully navigate on the road (Bojarski et al., 2016). However, advances in deep learning are not yet applied systematically to this task. In this work I used a simulated environment in order to implement and compare several methods for controlling autonomous navigation behavior using a single standard camera input device to sense the environmental state. The simulator contained a simulated car with a camera mounted on the top to gather visual data while being operated by a human controller on a virtual driving environment. The gathered data were used to perform supervised training for building an autonomous controller to drive the same vehicle remotely over a local connection. I reproduced results from previous researchers who have used simple neural networks and other ML techniques to guide similar test vehicles using a single camera. I compared these results with more complex deep neural network controllers to see if they can improve navigation performance based on past methods on measures of speed, distance, and other performance metrics on unseen simulated road driving tasks.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Artificial intelligence. $3 559380
650 4 $a Transportation. $3 558117
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0800
690 $a 0709
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Texas A&M University - Commerce. $b Computer Science. $3 1184441
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10689991 $z click for full text (PQDT)