國立虎尾科技大學 |

Control-Oriented Learning for Robotics and Dynamical Systems.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Control-Oriented Learning for Robotics and Dynamical Systems./
作者:	Richards, Spencer M.
面頁冊數:	1 online resource (172 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
標題:	Adaptation. -
電子資源:	click for full text (PQDT)
ISBN:	9798382622316

Control-Oriented Learning for Robotics and Dynamical Systems.
Richards, Spencer M.

Control-Oriented Learning for Robotics and Dynamical Systems. - 1 online resource (172 pages)

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

Thesis (Ph.D.)--Stanford University, 2023.

Includes bibliographical references

Data-driven learning for robotics is ultimately done in the interest of informing decision-making and control, particularly in unseen and unstructured environments. This thesis is centered on the concept of control-oriented learning, whereby learning is attuned to this desired goal, rather than to naively fit models to data. To this end, this thesis presents novel methodologies that tailor model learning towards closed-loop feedback control for robotic systems.In Part I of this thesis, we focus on the offline learning setting. We leverage nonlinear control theory to regularize data-driven model fitting optimization problems to be better aligned with the task of trajectory tracking. In Chapter 2, we propose to do this by adding constraints to the learning problem that encourage the learned model to be stabilizable by jointly learning a dynamics model and a control-theoretic certificate which guarantees the existence of robust tracking controllers for arbitrary open-loop trajectories generated with the learned model. In Chapter 3, we take a different approach by embedding intrinsic factorized structureinto our learned dynamics model that engenders the immediate synthesis of a performant tracking controller. Whether through constraints or model structure, we demonstrate that imbuing the offline learning problem with control-theoretic notions results in a model that performs better in closed-loop control online.In Part II of this thesis, we shift our focus to the online learning setting through the lens of adaptive control. In Chapter 4, we propose to learn a feature basis for adapting dynamics models offline through differentiable closed-loop simulation of classical adaptive control laws with parametric dynamics models. Ultimately, this takes the form of a meta-learning framework that links gradient descent on a trajectory tracking performance metric with a parametric representation of any unknown dynamics residual and feedback gains defining the adaptive control law. In Chapter 5, we generalize classical adaptive control concepts, namely stable concurrent estimation and certainty-equivalent cancellation of uncertain dynamics terms, to the robust model predictive control setting. Our approach allows us to couple classic online adaptation schemes, parameter uncertainty bounds, and robust model predictive control feedback that maintains safety through state and input constraint satisfaction, while decreasing conservatism in our uncertainty bounds over time.We conclude this thesis with a discussion of possible future avenues of work towards better synergy between learning modules in the autonomy stack and online closed-loop deployment objectives.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798382622316Subjects--Topical Terms:

1465331
Adaptation.
Index Terms--Genre/Form:

554714
Electronic books.

Control-Oriented Learning for Robotics and Dynamical Systems.
LDR:03922ntm a22003257 4500 001 1151883
005 20241118135854.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798382622316
035 $a (MiAaPQ)AAI30982559
035 $a (MiAaPQ)STANFORDjv434vz2493
035 $a AAI30982559
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Richards, Spencer M. $3 1478723
245 1 0 $a Control-Oriented Learning for Robotics and Dynamical Systems.
264 0 $c 2023
300 $a 1 online resource (172 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: 85-11, Section: B.
500 $a Advisor: Pavone, Marco;Schwager, Mac;Pavone, Marco;Boyd, Stephen.
502 $a Thesis (Ph.D.)--Stanford University, 2023.
504 $a Includes bibliographical references
520 $a Data-driven learning for robotics is ultimately done in the interest of informing decision-making and control, particularly in unseen and unstructured environments. This thesis is centered on the concept of control-oriented learning, whereby learning is attuned to this desired goal, rather than to naively fit models to data. To this end, this thesis presents novel methodologies that tailor model learning towards closed-loop feedback control for robotic systems.In Part I of this thesis, we focus on the offline learning setting. We leverage nonlinear control theory to regularize data-driven model fitting optimization problems to be better aligned with the task of trajectory tracking. In Chapter 2, we propose to do this by adding constraints to the learning problem that encourage the learned model to be stabilizable by jointly learning a dynamics model and a control-theoretic certificate which guarantees the existence of robust tracking controllers for arbitrary open-loop trajectories generated with the learned model. In Chapter 3, we take a different approach by embedding intrinsic factorized structureinto our learned dynamics model that engenders the immediate synthesis of a performant tracking controller. Whether through constraints or model structure, we demonstrate that imbuing the offline learning problem with control-theoretic notions results in a model that performs better in closed-loop control online.In Part II of this thesis, we shift our focus to the online learning setting through the lens of adaptive control. In Chapter 4, we propose to learn a feature basis for adapting dynamics models offline through differentiable closed-loop simulation of classical adaptive control laws with parametric dynamics models. Ultimately, this takes the form of a meta-learning framework that links gradient descent on a trajectory tracking performance metric with a parametric representation of any unknown dynamics residual and feedback gains defining the adaptive control law. In Chapter 5, we generalize classical adaptive control concepts, namely stable concurrent estimation and certainty-equivalent cancellation of uncertain dynamics terms, to the robust model predictive control setting. Our approach allows us to couple classic online adaptation schemes, parameter uncertainty bounds, and robust model predictive control feedback that maintains safety through state and input constraint satisfaction, while decreasing conservatism in our uncertainty bounds over time.We conclude this thesis with a discussion of possible future avenues of work towards better synergy between learning modules in the autonomy stack and online closed-loop deployment objectives.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Adaptation. $3 1465331
650 4 $a Robotics. $3 561941
655 7 $a Electronic books. $2 local $3 554714
690 $a 0771
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Stanford University. $3 1184533
773 0 $t Dissertations Abstracts International $g 85-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30982559 $z click for full text (PQDT)