東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

Sensor Directed AI-Based Robot Task Planning in Unstructured Environments.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Sensor Directed AI-Based Robot Task Planning in Unstructured Environments./
Author:	Mounesisohi, Alireza.
Description:	1 online resource (131 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 83-11, Section: B.
Contained By:	Dissertations Abstracts International83-11B.
Subject:	Artificial intelligence. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28965609click for full text (PQDT)
ISBN:	9798438735984

Sensor Directed AI-Based Robot Task Planning in Unstructured Environments.
Mounesisohi, Alireza.

Sensor Directed AI-Based Robot Task Planning in Unstructured Environments. - 1 online resource (131 pages)

Source: Dissertations Abstracts International, Volume: 83-11, Section: B.

Thesis (Ph.D.)--University of California, Davis, 2022.

Includes bibliographical references

This dissertation aims to improve methods for sensor-guided intelligent robotic task planning in unstructured environments. It will examine two fully unstructured environments: roadway maintenance and maintenance of space habitats. Maintenance automation of roadways and space habitats using robotic systems requires sensors and intelligent planning since both environments are highly unstructured. Robotic systems for automating roadway maintenance functions are typically installed on moving maintenance vehicles and must account for the unstructured nature of roadway traffic and conditions. In space habitats, when astronauts are not present, disturbances can perturb the environment, requiring sensor-driven and task planning robotic systems to deal with the habitat changes when performing maintenance functions.This dissertation first considers the automation of roadway crack cleaning or sealing using a vehicle-based robotic system. It develops a machine-vision based task planning system to automatically detect and map roadway cracks and guide a manipulator following a crack on the pavement. The work in this area is limited to roadway edge cracks that are approximately straight compared to alligator pavement cracks. The results are demonstrated experimentally on a linear device used to mimic the motion of vehicle-based robotic systems.Space habitats are very structured until a perturbation occurs due to a malfunction or movement of items within the habitat or in robotic interactions with on-board manufacturing as new parts are being fabricated. Robotic interaction with 3D printing manufacturing in space habitats is the second unstructured environment considered in this dissertation. A sensor-directed task planning and simulation method is developed which can autonomously fine-tune a robotic motion plan during interactions with the objects to be handled and address changes in objects configurations due to perturbations that can occur in the robot task space. As a result, this sensor-directed robotic system with task planning capabilities can be used for simulation and verification of several On-board Manufacturing (OBM) and maintenance operations.

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

Mode of access: World Wide Web

ISBN: 9798438735984Subjects--Topical Terms:

516317
Artificial intelligence.
Subjects--Index Terms:

Sensor directedIndex Terms--Genre/Form:

542853
Electronic books.

Sensor Directed AI-Based Robot Task Planning in Unstructured Environments.
LDR:03499nmm a2200373K 4500 001 2353092
005 20221214062749.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798438735984
035 $a (MiAaPQ)AAI28965609
035 $a AAI28965609
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Mounesisohi, Alireza. $3 3693425
245 1 0 $a Sensor Directed AI-Based Robot Task Planning in Unstructured Environments.
264 0 $c 2022
300 $a 1 online resource (131 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: Dissertations Abstracts International, Volume: 83-11, Section: B.
500 $a Advisor: Ravani, Bahram.
502 $a Thesis (Ph.D.)--University of California, Davis, 2022.
504 $a Includes bibliographical references
520 $a This dissertation aims to improve methods for sensor-guided intelligent robotic task planning in unstructured environments. It will examine two fully unstructured environments: roadway maintenance and maintenance of space habitats. Maintenance automation of roadways and space habitats using robotic systems requires sensors and intelligent planning since both environments are highly unstructured. Robotic systems for automating roadway maintenance functions are typically installed on moving maintenance vehicles and must account for the unstructured nature of roadway traffic and conditions. In space habitats, when astronauts are not present, disturbances can perturb the environment, requiring sensor-driven and task planning robotic systems to deal with the habitat changes when performing maintenance functions.This dissertation first considers the automation of roadway crack cleaning or sealing using a vehicle-based robotic system. It develops a machine-vision based task planning system to automatically detect and map roadway cracks and guide a manipulator following a crack on the pavement. The work in this area is limited to roadway edge cracks that are approximately straight compared to alligator pavement cracks. The results are demonstrated experimentally on a linear device used to mimic the motion of vehicle-based robotic systems.Space habitats are very structured until a perturbation occurs due to a malfunction or movement of items within the habitat or in robotic interactions with on-board manufacturing as new parts are being fabricated. Robotic interaction with 3D printing manufacturing in space habitats is the second unstructured environment considered in this dissertation. A sensor-directed task planning and simulation method is developed which can autonomously fine-tune a robotic motion plan during interactions with the objects to be handled and address changes in objects configurations due to perturbations that can occur in the robot task space. As a result, this sensor-directed robotic system with task planning capabilities can be used for simulation and verification of several On-board Manufacturing (OBM) and maintenance operations.
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 Remote sensing. $3 535394
650 4 $a Robotics. $3 519753
653 $a Sensor directed
653 $a Task planning
653 $a Unstructured environments
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0799
690 $a 0771
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of California, Davis. $b Mechanical and Aerospace Engineering. $3 3190211
773 0 $t Dissertations Abstracts International $g 83-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28965609 $z click for full text (PQDT)