國立虎尾科技大學 |

Data-Driven Adaptive Optimal Tracking and Its Applications to Intelligent Transportation Systems.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Data-Driven Adaptive Optimal Tracking and Its Applications to Intelligent Transportation Systems./
作者:	Gao, Weinan.
面頁冊數:	1 online resource (173 pages)
附註:	Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9781369850536

Data-Driven Adaptive Optimal Tracking and Its Applications to Intelligent Transportation Systems.
Gao, Weinan.

Data-Driven Adaptive Optimal Tracking and Its Applications to Intelligent Transportation Systems. - 1 online resource (173 pages)

Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.

Thesis (Ph.D.)--Polytechnic Institute of New York University, 2017.

Includes bibliographical references

In many emerging engineering applications, constructing an accurate model from first principles is a hard and time-consuming task which renders traditional model-based control approaches impractical. With the recent development of information science and technologies, scientists and engineers are actively seeking efficient ways to develop data-driven intelligent control systems that are robust, adaptive and reliable for uncertain or unknown environments. Adaptive dynamic programming (ADP) is a data-driven, non-model-based approach for control design in complex systems. This dissertation includes our recent contributions to the developments of ADP for data-driven adaptive optimal tracking control and robust adaptive optimal output-feedback control. We illustrate their applications in intelligent transportation systems as well.

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

Mode of access: World Wide Web

ISBN: 9781369850536Subjects--Topical Terms:

596380
Electrical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Data-Driven Adaptive Optimal Tracking and Its Applications to Intelligent Transportation Systems.
LDR:04339ntm a2200361K 4500 001 913926
005 20180628100931.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9781369850536
035 $a (MiAaPQ)AAI10281873
035 $a (MiAaPQ)poly:10361
035 $a AAI10281873
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Gao, Weinan. $3 1186958
245 1 0 $a Data-Driven Adaptive Optimal Tracking and Its Applications to Intelligent Transportation Systems.
264 0 $c 2017
300 $a 1 online resource (173 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: 78-10(E), Section: B.
500 $a Adviser: Zhong-Ping Jiang.
502 $a Thesis (Ph.D.)--Polytechnic Institute of New York University, 2017.
504 $a Includes bibliographical references
520 $a In many emerging engineering applications, constructing an accurate model from first principles is a hard and time-consuming task which renders traditional model-based control approaches impractical. With the recent development of information science and technologies, scientists and engineers are actively seeking efficient ways to develop data-driven intelligent control systems that are robust, adaptive and reliable for uncertain or unknown environments. Adaptive dynamic programming (ADP) is a data-driven, non-model-based approach for control design in complex systems. This dissertation includes our recent contributions to the developments of ADP for data-driven adaptive optimal tracking control and robust adaptive optimal output-feedback control. We illustrate their applications in intelligent transportation systems as well.
520 $a Our attention is first focused on solving adaptive optimal output regulation problems of continuous-time linear systems. Data-driven controllers are designed using ADP to achieve both non-vanishing disturbance rejection and asymptotic tracking in an optimal sense. This problem is essentially challenging since both the algebraic Riccati equation (ARE) and the regulator equation need to be solved without relying on the knowledge of system dynamics. We overcome this challenge by introducing a novel learning strategy which could not only efficiently solve the regulator equation by Sylvester map, but also iteratively approximate the solution to ARE. This strategy is extended to tackle adaptive optimal tracking control problems for nonlinear strict-feedback systems. A novel successive approximation method is proposed to solve a positive-semidefinite Hamilton-Jacobi-Bellman (HJB) equation with assured convergence.
520 $a Then, through robust adaptive dynamic programming, we study the robust optimal output-feedback controller design issue for a class of continuous-time interconnected systems with nonlinear dynamic uncertainties. The unmeasurable state can be reconstructed in terms of sampled input/output data, whereby we can design a robust adaptive optimal controller. We achieve the global asymptotic stability of the closed-loop interconnected system based on a combined application of Lyapunov theory, sampled-data system theory, and nonlinear small-gain theory.
520 $a Last but not least, we develop a next-generation intelligent cruise controller for connected vehicles under the framework of ADP. An approximate optimal cruise control policy is learned through collected online motion data from vehicles without relying on the knowledge of both human and vehicle models. This control policy can increase traffic throughput while reducing the fuel usage. Most importantly, the stability of the connected vehicle system, which is closely related to safety, is ensured. An extension to the connected vehicle system with strong nonlinear dynamics is studied through global adaptive dynamic programming, which is a tool for data-driven controller design such that the closed-loop system is globally asymptotically stable at an equilibrium of interest.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
650 4 $a Engineering. $3 561152
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0537
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Polytechnic Institute of New York University. $b Electrical and Computer Engineering. $3 1182851
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10281873 $z click for full text (PQDT)