國立虎尾科技大學 |

A reinforcement learning approach to predictive control design : = Autonomous vehicle applications.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	A reinforcement learning approach to predictive control design :/
其他題名:	Autonomous vehicle applications.
作者:	Jardine, P. Travis.
面頁冊數:	1 online resource (140 pages)
附註:	Source: Dissertation Abstracts International, Volume: 76-07C.
Contained By:	Dissertation Abstracts International76-07C.
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)

A reinforcement learning approach to predictive control design : = Autonomous vehicle applications.
Jardine, P. Travis.

A reinforcement learning approach to predictive control design :Autonomous vehicle applications. - 1 online resource (140 pages)

Source: Dissertation Abstracts International, Volume: 76-07C.

Thesis (Ph.D.)--Queen's University (Canada), 2018.

Includes bibliographical references

This research investigates the use of learning techniques to select control parameters in the Model Predictive Control (MPC) of autonomous vehicles. The general problem of having a vehicle track a target while adhering to constraints and minimizing control effort is defined. We further expand the problem to consider a vehicle for which the underlying dynamics are not well known. A game of Finite Action-Set Learning Automata (FALA) is used to select the weighting parameters in the MPC cost function. Fast Orthogonal Search (FOS) is combined with a Kalman Filter to simultaneously identify the model while estimating the system states. Planar inequality constraints are used to avoid spherical obstacles. The performance of these techniques is assessed for applications involving ground and aerial vehicles. Simulation and experimental results demonstrate that the combined FOS-FALA architecture reduces the overall number of design parameters that must be selected. The amount of reduction depends on the specific application. For the differential drive robot case considered here, the number for parameters was reduced from six to one. Furthermore, the learning strategy links the selection of these parameters to the desired performance. This is a significant improvement over the typical approach of trial and error.

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

Mode of access: World Wide Web

Subjects--Topical Terms:

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

554714
Electronic books.

A reinforcement learning approach to predictive control design : = Autonomous vehicle applications.
LDR:02577ntm a2200337Ki 4500 001 917922
005 20181022132250.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
035 $a (MiAaPQ)AAI10857294
035 $a (MiAaPQ)QueensUCan197424245
035 $a AAI10857294
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Jardine, P. Travis. $3 1192118
245 1 2 $a A reinforcement learning approach to predictive control design : $b Autonomous vehicle applications.
264 0 $c 2018
300 $a 1 online resource (140 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: 76-07C.
500 $a Advisers: Shahram Yousefi; Sidney Givigi.
502 $a Thesis (Ph.D.)--Queen's University (Canada), 2018.
504 $a Includes bibliographical references
520 $a This research investigates the use of learning techniques to select control parameters in the Model Predictive Control (MPC) of autonomous vehicles. The general problem of having a vehicle track a target while adhering to constraints and minimizing control effort is defined. We further expand the problem to consider a vehicle for which the underlying dynamics are not well known. A game of Finite Action-Set Learning Automata (FALA) is used to select the weighting parameters in the MPC cost function. Fast Orthogonal Search (FOS) is combined with a Kalman Filter to simultaneously identify the model while estimating the system states. Planar inequality constraints are used to avoid spherical obstacles. The performance of these techniques is assessed for applications involving ground and aerial vehicles. Simulation and experimental results demonstrate that the combined FOS-FALA architecture reduces the overall number of design parameters that must be selected. The amount of reduction depends on the specific application. For the differential drive robot case considered here, the number for parameters was reduced from six to one. Furthermore, the learning strategy links the selection of these parameters to the desired performance. This is a significant improvement over the typical approach of trial and error.
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 Computer engineering. $3 569006
650 4 $a Automotive engineering. $3 1104081
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0464
690 $a 0540
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Queen's University (Canada). $3 1148613
773 0 $t Dissertation Abstracts International $g 76-07C.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10857294 $z click for full text (PQDT)