國立虎尾科技大學 |

Analysis of Continuous Learning Models For Trajectory Representation.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Analysis of Continuous Learning Models For Trajectory Representation./
作者:	Norman, Kendal Graham.
面頁冊數:	1 online resource (52 pages)
附註:	Source: Masters Abstracts International, Volume: 84-12.
Contained By:	Masters Abstracts International84-12.
標題:	Mathematics. -
電子資源:	click for full text (PQDT)
ISBN:	9798379667160

Analysis of Continuous Learning Models For Trajectory Representation.
Norman, Kendal Graham.

Analysis of Continuous Learning Models For Trajectory Representation. - 1 online resource (52 pages)

Source: Masters Abstracts International, Volume: 84-12.

Thesis (M.Sc.)--Purdue University, 2023.

Includes bibliographical references

Trajectory planning is a field with widespread utility, and imitation learning pipelines show promise as an accessible training method for trajectory planning. MPNet is the state of the art for imitation learning with respect to success rates. MPNet has two general components to its runtime: a neural network predicts the location of the next anchor point in a trajectory, and then planning infrastructure applies sampling-based techniques to produce near-optimal, collision-less paths. This distinction between the two parts of MPNet prompts investigation into the role of the neural architectures in the Neural Motion Planning pipeline, to discover where improvements can be made. This thesis seeks to explore the importance of neural architecture choice by removing the planning structures, and comparing MPNet's feedforward anchor point predictor with that of a continuous model trained to output a continuous trajectory from start to goal. A new state of the art model in continuous learning is the Neural Flow model. As a continuous model, it possess a low standard deviation runtime which can be properly leveraged in the absence of planning infrastructure. Neural Flows also output smooth, continuous trajectory curves that serve to reduce noisy path outputs in the absence of lazy vertex contraction. This project analyzes the performance of MPNet, Resnet Flow, and Coupling Flow models when sampling-based planning tools such as dropout, lazy vertex contraction, and replanning are removed. Each neural planner is trained end-to-end in an imitation learning pipeline utilizing a simple feedforward encoder, a CNN-based encoder, and a Pointnet encoder to encode the environment, for purposes of comparison. Results indicate that performance is competitive, with Neural Flows slightly outperforming MPNet's success rates on our reduced dataset in Simple2D, and being slighty outperformed by MPNet with respect to collision penetration distance in our UR5 Cubby test suite. These results indicate that continuous models can compete with the performance of anchor point predictor models when sampling-based planning techniques are not applied. Neural Flow models also have other benefits that anchor point predictors do not, like continuity guarantees, the ability to select a proportional location in a trajectory to output, and smoothness.

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

Mode of access: World Wide Web

ISBN: 9798379667160Subjects--Topical Terms:

527692
Mathematics.
Index Terms--Genre/Form:

554714
Electronic books.

Analysis of Continuous Learning Models For Trajectory Representation.
LDR:03581ntm a22003617 4500 001 1151993
005 20241125080204.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379667160
035 $a (MiAaPQ)AAI30501577
035 $a (MiAaPQ)Purdue22681492
035 $a AAI30501577
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Norman, Kendal Graham. $3 1478863
245 1 0 $a Analysis of Continuous Learning Models For Trajectory Representation.
264 0 $c 2023
300 $a 1 online resource (52 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: Masters Abstracts International, Volume: 84-12.
500 $a Advisor: Qureshi, Ahmed H.
502 $a Thesis (M.Sc.)--Purdue University, 2023.
504 $a Includes bibliographical references
520 $a Trajectory planning is a field with widespread utility, and imitation learning pipelines show promise as an accessible training method for trajectory planning. MPNet is the state of the art for imitation learning with respect to success rates. MPNet has two general components to its runtime: a neural network predicts the location of the next anchor point in a trajectory, and then planning infrastructure applies sampling-based techniques to produce near-optimal, collision-less paths. This distinction between the two parts of MPNet prompts investigation into the role of the neural architectures in the Neural Motion Planning pipeline, to discover where improvements can be made. This thesis seeks to explore the importance of neural architecture choice by removing the planning structures, and comparing MPNet's feedforward anchor point predictor with that of a continuous model trained to output a continuous trajectory from start to goal. A new state of the art model in continuous learning is the Neural Flow model. As a continuous model, it possess a low standard deviation runtime which can be properly leveraged in the absence of planning infrastructure. Neural Flows also output smooth, continuous trajectory curves that serve to reduce noisy path outputs in the absence of lazy vertex contraction. This project analyzes the performance of MPNet, Resnet Flow, and Coupling Flow models when sampling-based planning tools such as dropout, lazy vertex contraction, and replanning are removed. Each neural planner is trained end-to-end in an imitation learning pipeline utilizing a simple feedforward encoder, a CNN-based encoder, and a Pointnet encoder to encode the environment, for purposes of comparison. Results indicate that performance is competitive, with Neural Flows slightly outperforming MPNet's success rates on our reduced dataset in Simple2D, and being slighty outperformed by MPNet with respect to collision penetration distance in our UR5 Cubby test suite. These results indicate that continuous models can compete with the performance of anchor point predictor models when sampling-based planning techniques are not applied. Neural Flow models also have other benefits that anchor point predictors do not, like continuity guarantees, the ability to select a proportional location in a trajectory to output, and smoothness.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Mathematics. $3 527692
650 4 $a Civil engineering. $3 561339
650 4 $a Neural networks. $3 1011215
650 4 $a Ordinary differential equations. $3 1473835
650 4 $a Planning. $3 660157
650 4 $a Success. $3 571577
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0543
690 $a 0501
690 $a 0405
710 2 $a Purdue University. $3 1184550
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Masters Abstracts International $g 84-12.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30501577 $z click for full text (PQDT)