國立虎尾科技大學 |

Expanding the Limits of Vision-Based Autonomous Path Following.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Expanding the Limits of Vision-Based Autonomous Path Following./
作者:	Paton, Michael.
面頁冊數:	1 online resource (155 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
Contained By:	Dissertation Abstracts International79-08B(E).
標題:	Robotics. -
電子資源:	click for full text (PQDT)
ISBN:	9780355813586

Expanding the Limits of Vision-Based Autonomous Path Following.
Paton, Michael.

Expanding the Limits of Vision-Based Autonomous Path Following. - 1 online resource (155 pages)

Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.

Thesis (Ph.D.)--University of Toronto (Canada), 2018.

Includes bibliographical references

Autonomous path-following systems allow robots to traverse large-scale networks of paths using on-board sensors. These methods are well suited for applications that involve repeated traversals of constrained paths such as factory floors, orchards, and mines. Through the use of inexpensive, commercial, vision sensors, these algorithms have the potential to enable robotic applications across multiple industries. However, these applications will demand algorithms capable of long-term autonomy. This poses a difficult challenge for vision-based systems in unstructured and outdoor environments, whose appearances are highly variable. While techniques have been developed to perform localization across extreme appearance change, most are not suitable or untested for vision-in-the-loop systems such as autonomous path following, which requires continuous metric localization to keep the robot driving. This thesis extends the performance of vision-based autonomous path following through the development of novel localization and mapping techniques. First, we present the following generic localization frameworks: i) a many-to-one localization framework that combines data associations from independent sources of information into single state-estimation problems, and ii) a multi-experience localization and mapping system that provides metric localization to the manually taught path across extreme appearance change using bridging experiences gathered during autonomous operation. We use these frameworks to develop three novel autonomous path-following systems: i) a lighting-resistant system capable of autonomous operation across daily lighting change through the fusion of data from traditional-grayscale and color-constant images, ii) a multi-stereo system that extends the field-of-view of the algorithm by fusing data from multiple stereo cameras, and iii) a multi-experience system that uses both localization frameworks to achieve reliable localization across appearance change as extreme as night vs. day and winter vs. summer. These systems are validated through a collection of extensive field tests covering over 213 km of vision-in-the-loop autonomous driving across a wide variety of environments and appearance change with an autonomy rate of 99.7% of distance traveled.

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

Mode of access: World Wide Web

ISBN: 9780355813586Subjects--Topical Terms:

561941
Robotics.
Index Terms--Genre/Form:

554714
Electronic books.

Expanding the Limits of Vision-Based Autonomous Path Following.
LDR:03520ntm a2200337Ki 4500 001 918339
005 20181114145235.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780355813586
035 $a (MiAaPQ)AAI10686531
035 $a (MiAaPQ)toronto:16954
035 $a AAI10686531
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Paton, Michael. $3 1192638
245 1 0 $a Expanding the Limits of Vision-Based Autonomous Path Following.
264 0 $c 2018
300 $a 1 online resource (155 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: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
500 $a Adviser: Timothy D. Barfoot.
502 $a Thesis (Ph.D.)--University of Toronto (Canada), 2018.
504 $a Includes bibliographical references
520 $a Autonomous path-following systems allow robots to traverse large-scale networks of paths using on-board sensors. These methods are well suited for applications that involve repeated traversals of constrained paths such as factory floors, orchards, and mines. Through the use of inexpensive, commercial, vision sensors, these algorithms have the potential to enable robotic applications across multiple industries. However, these applications will demand algorithms capable of long-term autonomy. This poses a difficult challenge for vision-based systems in unstructured and outdoor environments, whose appearances are highly variable. While techniques have been developed to perform localization across extreme appearance change, most are not suitable or untested for vision-in-the-loop systems such as autonomous path following, which requires continuous metric localization to keep the robot driving. This thesis extends the performance of vision-based autonomous path following through the development of novel localization and mapping techniques. First, we present the following generic localization frameworks: i) a many-to-one localization framework that combines data associations from independent sources of information into single state-estimation problems, and ii) a multi-experience localization and mapping system that provides metric localization to the manually taught path across extreme appearance change using bridging experiences gathered during autonomous operation. We use these frameworks to develop three novel autonomous path-following systems: i) a lighting-resistant system capable of autonomous operation across daily lighting change through the fusion of data from traditional-grayscale and color-constant images, ii) a multi-stereo system that extends the field-of-view of the algorithm by fusing data from multiple stereo cameras, and iii) a multi-experience system that uses both localization frameworks to achieve reliable localization across appearance change as extreme as night vs. day and winter vs. summer. These systems are validated through a collection of extensive field tests covering over 213 km of vision-in-the-loop autonomous driving across a wide variety of environments and appearance change with an autonomy rate of 99.7% of distance traveled.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Robotics. $3 561941
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0771
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Toronto (Canada). $b Aerospace Science and Engineering. $3 845686
773 0 $t Dissertation Abstracts International $g 79-08B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10686531 $z click for full text (PQDT)