An automation system for vehicle driveability evaluation using machine learning
The drivability is one of the important aspects of vehicle dynamic performances. To ensure quality of the drivability performance, comprehensive screening evaluation is necessary by controlling both complicated driver operation and vehicle behavior. However, it is not straightforward for engineers t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | Japanese |
| Published: |
The Japan Society of Mechanical Engineers
2022-10-01
|
| Series: | Nihon Kikai Gakkai ronbunshu |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/transjsme/88/915/88_22-00219/_pdf/-char/en |
| _version_ | 1811303639634935808 |
|---|---|
| author | Hisashi TAJIMA Kohei SHINTANI Azuki OGOSHI Shota KITANO Motofumi IWATA |
| author_facet | Hisashi TAJIMA Kohei SHINTANI Azuki OGOSHI Shota KITANO Motofumi IWATA |
| author_sort | Hisashi TAJIMA |
| collection | DOAJ |
| description | The drivability is one of the important aspects of vehicle dynamic performances. To ensure quality of the drivability performance, comprehensive screening evaluation is necessary by controlling both complicated driver operation and vehicle behavior. However, it is not straightforward for engineers to handle all combinations of test patterns with limited resources while considering complex control logic and program carefully. This paper proposes a novel automated drivability screening and exploration system by introducing Bayesian active learning (BAL). The proposed system is composed of two key elements such as automated evaluation sub-system and screening and exploring sub-system. In the automated evaluation sub-system, driver model is used to mimic various operation patters of expert drivers and corresponded drivability performance is evaluated automatically using Power-Train Virtual and Real Simulator (PT-VRS). The automated exploring sub-system is used to screen severe condition for drivability and explore feasible region of design space described by control parameters. An effective sampling strategy is introduced based on BAL. In the BAL, Gaussian Process models of drivability performance evaluated by PT-VARS is trained. Based on the posterior distributions of trained Gaussian Processes models, acquisition functions are evaluated and maximized to generate new sampling points. To show effectiveness of the proposed system, an example is demonstrated. |
| first_indexed | 2024-04-13T07:51:22Z |
| format | Article |
| id | doaj.art-aafe653d30ed476bbfed06580183018b |
| institution | Directory Open Access Journal |
| issn | 2187-9761 |
| language | Japanese |
| last_indexed | 2024-04-13T07:51:22Z |
| publishDate | 2022-10-01 |
| publisher | The Japan Society of Mechanical Engineers |
| record_format | Article |
| series | Nihon Kikai Gakkai ronbunshu |
| spelling | doaj.art-aafe653d30ed476bbfed06580183018b2022-12-22T02:55:31ZjpnThe Japan Society of Mechanical EngineersNihon Kikai Gakkai ronbunshu2187-97612022-10-018891522-0021922-0021910.1299/transjsme.22-00219transjsmeAn automation system for vehicle driveability evaluation using machine learningHisashi TAJIMA0Kohei SHINTANI1Azuki OGOSHI2Shota KITANO3Motofumi IWATA4Toyota Motor CorporationToyota Motor CorporationToyota Motor CorporationToyota Motor CorporationToyota Motor CorporationThe drivability is one of the important aspects of vehicle dynamic performances. To ensure quality of the drivability performance, comprehensive screening evaluation is necessary by controlling both complicated driver operation and vehicle behavior. However, it is not straightforward for engineers to handle all combinations of test patterns with limited resources while considering complex control logic and program carefully. This paper proposes a novel automated drivability screening and exploration system by introducing Bayesian active learning (BAL). The proposed system is composed of two key elements such as automated evaluation sub-system and screening and exploring sub-system. In the automated evaluation sub-system, driver model is used to mimic various operation patters of expert drivers and corresponded drivability performance is evaluated automatically using Power-Train Virtual and Real Simulator (PT-VRS). The automated exploring sub-system is used to screen severe condition for drivability and explore feasible region of design space described by control parameters. An effective sampling strategy is introduced based on BAL. In the BAL, Gaussian Process models of drivability performance evaluated by PT-VARS is trained. Based on the posterior distributions of trained Gaussian Processes models, acquisition functions are evaluated and maximized to generate new sampling points. To show effectiveness of the proposed system, an example is demonstrated.https://www.jstage.jst.go.jp/article/transjsme/88/915/88_22-00219/_pdf/-char/envehicle dynamicsdrivabilitygaussian processbayesian active learningautomatic evaluation |
| spellingShingle | Hisashi TAJIMA Kohei SHINTANI Azuki OGOSHI Shota KITANO Motofumi IWATA An automation system for vehicle driveability evaluation using machine learning Nihon Kikai Gakkai ronbunshu vehicle dynamics drivability gaussian process bayesian active learning automatic evaluation |
| title | An automation system for vehicle driveability evaluation using machine learning |
| title_full | An automation system for vehicle driveability evaluation using machine learning |
| title_fullStr | An automation system for vehicle driveability evaluation using machine learning |
| title_full_unstemmed | An automation system for vehicle driveability evaluation using machine learning |
| title_short | An automation system for vehicle driveability evaluation using machine learning |
| title_sort | automation system for vehicle driveability evaluation using machine learning |
| topic | vehicle dynamics drivability gaussian process bayesian active learning automatic evaluation |
| url | https://www.jstage.jst.go.jp/article/transjsme/88/915/88_22-00219/_pdf/-char/en |
| work_keys_str_mv | AT hisashitajima anautomationsystemforvehicledriveabilityevaluationusingmachinelearning AT koheishintani anautomationsystemforvehicledriveabilityevaluationusingmachinelearning AT azukiogoshi anautomationsystemforvehicledriveabilityevaluationusingmachinelearning AT shotakitano anautomationsystemforvehicledriveabilityevaluationusingmachinelearning AT motofumiiwata anautomationsystemforvehicledriveabilityevaluationusingmachinelearning AT hisashitajima automationsystemforvehicledriveabilityevaluationusingmachinelearning AT koheishintani automationsystemforvehicledriveabilityevaluationusingmachinelearning AT azukiogoshi automationsystemforvehicledriveabilityevaluationusingmachinelearning AT shotakitano automationsystemforvehicledriveabilityevaluationusingmachinelearning AT motofumiiwata automationsystemforvehicledriveabilityevaluationusingmachinelearning |