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

Real-Time Hierarchical Classification of Motion Intent for Wearable Robotics.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Real-Time Hierarchical Classification of Motion Intent for Wearable Robotics./
作者:	Narayan, Ashwin.
面頁冊數:	1 online resource (174 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-09, Section: B.
Contained By:	Dissertations Abstracts International84-09B.
標題:	Ankle. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30339997click for full text (PQDT)
ISBN:	9798374483239

Real-Time Hierarchical Classification of Motion Intent for Wearable Robotics.
Narayan, Ashwin.

Real-Time Hierarchical Classification of Motion Intent for Wearable Robotics. - 1 online resource (174 pages)

Source: Dissertations Abstracts International, Volume: 84-09, Section: B.

Thesis (Ph.D.)--National University of Singapore (Singapore), 2022.

Includes bibliographical references

Wearable robotic devices like exoskeletons and robotic prostheses have the potential to address many global health challenges associated with an aging population.Sensing the wearable robot user's motion intent is a major challenge in the field of wearable robot control. Accurate motion intent detection allows assistive forces to be delivered with the right timing and magnitude to the biological joints.This thesis presents a novel strategy for classifying locomotion modes for motion intent detection. Based on the idea that human motion can be described at multiple levels of specificity, a deep neural network based hierarchical classifier is developed that performs classification of locomotion mode labels at multiple levels of specificity simultaneously.A high performance wearable IMU sensor network was developed for collecting real-time motion data. Using this sensor system a dataset of IMU motion data was collected for training and offline evaluation of the hierarchical classifier. The configuration of the IMU sensors and motions performed during the experiment were targeted at the control of a uni-lateral ankle-knee exoskeleton for post-stroke rehabilitation.The results of the offline evaluation indicate that the method achieves accurate classification of locomotion modes and can classify less specific locomotion modes earlier than more specific locomotion modes as hypothesized.To validate the practicality of the method, the classifier is used for the real-time control of the aforementioned uni-lateral lower limb exoskeleton. The hierarchical classifier is improved, and converted into a form that can be run in hard real-time on an ARM based microcontroller. A custom real-time CAN Bus based IMU sensor network was developed to capture motion data for locomotion mode classification. A hierarchical control strategy is developed to map the output of the classifier to assistive forces to demonstrate the use of the hierarchical classification.The experimental results indicate that the real-time classification is performed accurately and in real-time when the exoskeleton control is active; and that the method is practical for the control of wearable robotic devices.

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

Mode of access: World Wide Web

ISBN: 9798374483239Subjects--Topical Terms:

3563106
Ankle.
Index Terms--Genre/Form:

542853
Electronic books.

Real-Time Hierarchical Classification of Motion Intent for Wearable Robotics.
LDR:03593nmm a2200421K 4500 001 2363800
005 20231127094602.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798374483239
035 $a (MiAaPQ)AAI30339997
035 $a (MiAaPQ)USingapore235774
035 $a AAI30339997
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Narayan, Ashwin. $3 3704575
245 1 0 $a Real-Time Hierarchical Classification of Motion Intent for Wearable Robotics.
264 0 $c 2022
300 $a 1 online resource (174 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: 84-09, Section: B.
500 $a Advisor: Haoyong, Yu.
502 $a Thesis (Ph.D.)--National University of Singapore (Singapore), 2022.
504 $a Includes bibliographical references
520 $a Wearable robotic devices like exoskeletons and robotic prostheses have the potential to address many global health challenges associated with an aging population.Sensing the wearable robot user's motion intent is a major challenge in the field of wearable robot control. Accurate motion intent detection allows assistive forces to be delivered with the right timing and magnitude to the biological joints.This thesis presents a novel strategy for classifying locomotion modes for motion intent detection. Based on the idea that human motion can be described at multiple levels of specificity, a deep neural network based hierarchical classifier is developed that performs classification of locomotion mode labels at multiple levels of specificity simultaneously.A high performance wearable IMU sensor network was developed for collecting real-time motion data. Using this sensor system a dataset of IMU motion data was collected for training and offline evaluation of the hierarchical classifier. The configuration of the IMU sensors and motions performed during the experiment were targeted at the control of a uni-lateral ankle-knee exoskeleton for post-stroke rehabilitation.The results of the offline evaluation indicate that the method achieves accurate classification of locomotion modes and can classify less specific locomotion modes earlier than more specific locomotion modes as hypothesized.To validate the practicality of the method, the classifier is used for the real-time control of the aforementioned uni-lateral lower limb exoskeleton. The hierarchical classifier is improved, and converted into a form that can be run in hard real-time on an ARM based microcontroller. A custom real-time CAN Bus based IMU sensor network was developed to capture motion data for locomotion mode classification. A hierarchical control strategy is developed to map the output of the classifier to assistive forces to demonstrate the use of the hierarchical classification.The experimental results indicate that the real-time classification is performed accurately and in real-time when the exoskeleton control is active; and that the method is practical for the control of wearable robotic devices.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Ankle. $3 3563106
650 4 $a Deep learning. $3 3554982
650 4 $a Prostheses. $3 3683608
650 4 $a Robots. $3 529507
650 4 $a Military bases. $3 3560116
650 4 $a Rehabilitation. $3 529790
650 4 $a Visualization. $3 586179
650 4 $a Probability distribution. $3 3562293
650 4 $a Robotics. $3 519753
650 4 $a Gait. $3 1362772
650 4 $a Age. $3 1486010
650 4 $a Aging. $3 543123
650 4 $a Sensors. $3 3549539
650 4 $a Medical research. $2 bicssc $3 1556686
650 4 $a Design. $3 518875
650 4 $a Probability. $3 518898
650 4 $a Illnesses. $3 3559962
650 4 $a Walking. $3 548733
650 4 $a Military studies. $3 2197382
650 4 $a Statistics. $3 517247
650 4 $a Therapy. $3 3343697
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0771
690 $a 0493
690 $a 0389
690 $a 0800
690 $a 0629
690 $a 0338
690 $a 0750
690 $a 0463
690 $a 0212
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a National University of Singapore (Singapore). $3 3352228
773 0 $t Dissertations Abstracts International $g 84-09B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30339997 $z click for full text (PQDT)