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

Learning Dominant Dynamics for Conti...

Alora, John Irvin,

Linked to FindBook

Google Book

Amazon

博客來

Learning Dominant Dynamics for Continuum Robot Control /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Learning Dominant Dynamics for Continuum Robot Control // John Irvin Alora.
Author:	Alora, John Irvin,
Description:	1 electronic resource (132 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
Contained By:	Dissertations Abstracts International86-12B.
Subject:	Robots. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31974636
ISBN:	9798311949101

Learning Dominant Dynamics for Continuum Robot Control /
Alora, John Irvin,

Learning Dominant Dynamics for Continuum Robot Control /John Irvin Alora. - 1 electronic resource (132 pages)

Source: Dissertations Abstracts International, Volume: 86-12, Section: B.

Continuum robots, which emulate biological organisms' dexterity and flexibility, hold transformative potential for terrestrial and extraterrestrial applications. While such capabilities present significant modeling and control challenges, these robots' highly dissipative nature allows their behavior to be explained by low-dimensional, dominant dynamics. Despite extensive research to uncover these dynamics, existing methodologies often fail to produce models that accurately capture them, hindering precise control in diverse and safety-critical tasks. This work addresses this gap by discovering these dynamics and leveraging them in a control methodology that enables real-time, high-precision motion planning and constraint handling.To achieve this, we develop a data-driven, model-based approach grounded in Spectral Submanifold Reduction (SSMR), a principled framework that extracts the dominant dynamics of continuum robots from limited sensor data. Our approach constructs faithful, low-dimensional models by leveraging the geometric structure of attracting invariant manifolds in the robots' phase space. By embedding these learned dynamics into a model predictive control (MPC) scheme, we achieve computationally efficient trajectory tracking while ensuring safety constraints are satisfied. To guarantee safety of SSMR and to establish theoretical guarantees on model accuracy, we derive error bounds on reduced-order approximations. Lastly, we extend SSMR to incorporate time-varying manifolds, improving robustness in highly dynamic regimes. We validate our approach through extensive simulations and hardware experiments on multiple continuum robot morphologies, demonstrating state-of-the-art tracking accuracy and constraint satisfaction compared to conventional model-based and model-free methods.Our results suggest that SSMR-based control offers a scalable and generalizable solution for deploying continuum robots in real-world, safety-critical environments. This work lays the foundation for future research in learning-based nonlinear control, particularly in scenarios requiring high precision under computational constraints, such as robotic surgery, deep-sea exploration, and space applications.

English

ISBN: 9798311949101Subjects--Topical Terms:

529507
Robots.

Learning Dominant Dynamics for Continuum Robot Control /
LDR:03473nmm a22003613i 4500 001 2433840
005 20250905091024.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798311949101
035 $a (MiAaPQD)AAI31974636
035 $a (MiAaPQD)Stanfordqq299vc2406
035 $a AAI31974636
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Alora, John Irvin, $e author. $3 3823607
245 1 0 $a Learning Dominant Dynamics for Continuum Robot Control / $c John Irvin Alora.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (132 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: 86-12, Section: B.
500 $a Advisors: Pavone, Marco Committee members: Alonso, Juan; Schwager, Mac; Bent, Stacey F.
502 $b Ph.D. $c Stanford University $d 2025.
520 $a Continuum robots, which emulate biological organisms' dexterity and flexibility, hold transformative potential for terrestrial and extraterrestrial applications. While such capabilities present significant modeling and control challenges, these robots' highly dissipative nature allows their behavior to be explained by low-dimensional, dominant dynamics. Despite extensive research to uncover these dynamics, existing methodologies often fail to produce models that accurately capture them, hindering precise control in diverse and safety-critical tasks. This work addresses this gap by discovering these dynamics and leveraging them in a control methodology that enables real-time, high-precision motion planning and constraint handling.To achieve this, we develop a data-driven, model-based approach grounded in Spectral Submanifold Reduction (SSMR), a principled framework that extracts the dominant dynamics of continuum robots from limited sensor data. Our approach constructs faithful, low-dimensional models by leveraging the geometric structure of attracting invariant manifolds in the robots' phase space. By embedding these learned dynamics into a model predictive control (MPC) scheme, we achieve computationally efficient trajectory tracking while ensuring safety constraints are satisfied. To guarantee safety of SSMR and to establish theoretical guarantees on model accuracy, we derive error bounds on reduced-order approximations. Lastly, we extend SSMR to incorporate time-varying manifolds, improving robustness in highly dynamic regimes. We validate our approach through extensive simulations and hardware experiments on multiple continuum robot morphologies, demonstrating state-of-the-art tracking accuracy and constraint satisfaction compared to conventional model-based and model-free methods.Our results suggest that SSMR-based control offers a scalable and generalizable solution for deploying continuum robots in real-world, safety-critical environments. This work lays the foundation for future research in learning-based nonlinear control, particularly in scenarios requiring high precision under computational constraints, such as robotic surgery, deep-sea exploration, and space applications.
546 $a English
590 $a School code: 0212
650 4 $a Robots. $3 529507
650 4 $a Geometry. $3 517251
650 4 $a Robotics. $3 519753
690 $a 0771
710 2 $a Stanford University. $e degree granting institution. $3 3765820
720 1 $a Pavone, Marco $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-12B.
790 $a 0212
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31974636