東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Deep Learning Based Simulation for Automotive Software Development.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Deep Learning Based Simulation for Automotive Software Development./
作者:	Parthasarathy, Dhasarathy.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	111 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-11, Section: B.
Contained By:	Dissertations Abstracts International83-11B.
標題:	Distributed control systems. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29071964
ISBN:	9798426872547

Deep Learning Based Simulation for Automotive Software Development.
Parthasarathy, Dhasarathy.

Deep Learning Based Simulation for Automotive Software Development. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 111 p.

Source: Dissertations Abstracts International, Volume: 83-11, Section: B.

Thesis (Ph.D.)--Chalmers Tekniska Hogskola (Sweden), 2022.

This item must not be sold to any third party vendors.

Context - The automotive industry is in the midst of a new reality where software is increasingly becoming the primary tool for delivering value to customers. While this has vastly improved their product offerings, vehicle manufacturers are increasingly facing the need to continuously develop, test, and deliver functionality, while maintaining high levels of quality. One important tool for achieving this is simulation-based testing where the external operating environment of a software system is simulated, enabling incremental development with rapid test feedback. However, the traditional practice of manually specifying simulation models for complex external environments involves immense engineering effort, while remaining vulnerable to inevitable assumptions and simplifications. Exploiting the increased availability of data that captures operational environments and scenarios from the field, this work takes a deep learning approach to train models that realistically simulate external environments, significantly increasing the credibility of simulation-driven software development.Contributions - First, focusing on simulating the input dependencies of automotive software functions, this work uses techniques of deep generative modeling to develop a framework for realistic test stimulus generation. Such models are trained self-supervised using recorded time-series field data and simulate the input environment much more credibly than manually specified models. With the credibility of stimulus generation being an important concern, an important concept of similarity as plausibility is introduced to evaluate the quality of generation during model training. Second, this work develops new techniques for sampling generative models that enable the controlled generation of test stimulus. Allowing testers to limit the range of scenarios considered for testing, the Metric-based Linear Interpolation (MLERP) sampling algorithm automatically chooses test stimuli that are verifiably similar to a user-supplied reference, and therefore measurably credible. While controllability eases the design of tests, credibility increases trust in the testing process. Third, recognizing that sampling may be an inefficient process for stimulus generation, this work develops a technique that extracts properties from actual code under test in order to automatically search for appropriate test stimuli within the specified range of test scenarios. Fourth, further addressing the question of credible stimulus generation, this work introduces techniques that examine training data for biases in sample representation. Overall, by taking a data-driven deep learning approach, techniques and tools developed in this work vastly expands the credibility of incremental automotive software development under simulated conditions.Future work - Work in the future plans to (1) expand the scope from openloop stimulus generation to include output dependencies including elements of feedback in closed-loop software systems, and (2) use trained models, instead of hand-coded rules, to understand and extract properties from code under test.

ISBN: 9798426872547Subjects--Topical Terms:

3689541
Distributed control systems.

Deep Learning Based Simulation for Automotive Software Development.
LDR:04181nmm a2200337 4500 001 2350092
005 20221020123853.5
008 241004s2022 ||||||||||||||||| ||eng d
020 $a 9798426872547
035 $a (MiAaPQ)AAI29071964
035 $a (MiAaPQ)Chalmers_SE528447
035 $a AAI29071964
040 $a MiAaPQ $c MiAaPQ
100 1 $a Parthasarathy, Dhasarathy. $3 3689540
245 1 0 $a Deep Learning Based Simulation for Automotive Software Development.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 111 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-11, Section: B.
502 $a Thesis (Ph.D.)--Chalmers Tekniska Hogskola (Sweden), 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Context - The automotive industry is in the midst of a new reality where software is increasingly becoming the primary tool for delivering value to customers. While this has vastly improved their product offerings, vehicle manufacturers are increasingly facing the need to continuously develop, test, and deliver functionality, while maintaining high levels of quality. One important tool for achieving this is simulation-based testing where the external operating environment of a software system is simulated, enabling incremental development with rapid test feedback. However, the traditional practice of manually specifying simulation models for complex external environments involves immense engineering effort, while remaining vulnerable to inevitable assumptions and simplifications. Exploiting the increased availability of data that captures operational environments and scenarios from the field, this work takes a deep learning approach to train models that realistically simulate external environments, significantly increasing the credibility of simulation-driven software development.Contributions - First, focusing on simulating the input dependencies of automotive software functions, this work uses techniques of deep generative modeling to develop a framework for realistic test stimulus generation. Such models are trained self-supervised using recorded time-series field data and simulate the input environment much more credibly than manually specified models. With the credibility of stimulus generation being an important concern, an important concept of similarity as plausibility is introduced to evaluate the quality of generation during model training. Second, this work develops new techniques for sampling generative models that enable the controlled generation of test stimulus. Allowing testers to limit the range of scenarios considered for testing, the Metric-based Linear Interpolation (MLERP) sampling algorithm automatically chooses test stimuli that are verifiably similar to a user-supplied reference, and therefore measurably credible. While controllability eases the design of tests, credibility increases trust in the testing process. Third, recognizing that sampling may be an inefficient process for stimulus generation, this work develops a technique that extracts properties from actual code under test in order to automatically search for appropriate test stimuli within the specified range of test scenarios. Fourth, further addressing the question of credible stimulus generation, this work introduces techniques that examine training data for biases in sample representation. Overall, by taking a data-driven deep learning approach, techniques and tools developed in this work vastly expands the credibility of incremental automotive software development under simulated conditions.Future work - Work in the future plans to (1) expand the scope from openloop stimulus generation to include output dependencies including elements of feedback in closed-loop software systems, and (2) use trained models, instead of hand-coded rules, to understand and extract properties from code under test.
590 $a School code: 0419.
650 4 $a Distributed control systems. $3 3689541
650 4 $a Physics. $3 516296
650 4 $a Deep learning. $3 3554982
650 4 $a Credibility. $3 3560860
650 4 $a Feedback. $3 677181
650 4 $a Software engineering. $3 559826
650 4 $a Sensors. $3 3549539
650 4 $a Vehicles. $3 2145288
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
650 4 $a Transportation. $3 555912
650 4 $a Engineering. $3 586835
690 $a 0605
690 $a 0800
690 $a 0984
690 $a 0537
690 $a 0709
710 2 $a Chalmers Tekniska Hogskola (Sweden). $3 1913472
773 0 $t Dissertations Abstracts International $g 83-11B.
790 $a 0419
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29071964