{"title":"Converting Driving Scenario Framework for Testing Self-Driving Systems","authors":"Keita Miura, Takuya Azumi","doi":"10.1109/EUC50751.2020.00015","DOIUrl":null,"url":null,"abstract":"This paper presents a converting driving scenarios to generate a format suitable for LGSVL simulator. Autonomous vehicles are developed worldwide. To reduce the test cost, virtual simulators are used in the automotive industry. However, the virtual simulators require simulation environments, such as roads, pedestrians, and vehicles. To set these parameters of many test cases is not efficient for developers. MATLAB/Simulink can create the scenarios graphically. Therefore, we proposed a framework to convert scenarios created with MATLAB/Simulink to a format suitable for LGSVL simulator which is an autonomous vehicle simulator. The converted scenarios can perform in LGSVL simulator like the scenarios defined with MATLAB/Simulink. Moreover, LGSVL simulator has cooperated with Autoware, which is an open-source self-driving system. This cooperation facilitates testing the self-driving systems. This framework can help developers create scenarios.","PeriodicalId":331605,"journal":{"name":"2020 IEEE 18th International Conference on Embedded and Ubiquitous Computing (EUC)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE 18th International Conference on Embedded and Ubiquitous Computing (EUC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EUC50751.2020.00015","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
This paper presents a converting driving scenarios to generate a format suitable for LGSVL simulator. Autonomous vehicles are developed worldwide. To reduce the test cost, virtual simulators are used in the automotive industry. However, the virtual simulators require simulation environments, such as roads, pedestrians, and vehicles. To set these parameters of many test cases is not efficient for developers. MATLAB/Simulink can create the scenarios graphically. Therefore, we proposed a framework to convert scenarios created with MATLAB/Simulink to a format suitable for LGSVL simulator which is an autonomous vehicle simulator. The converted scenarios can perform in LGSVL simulator like the scenarios defined with MATLAB/Simulink. Moreover, LGSVL simulator has cooperated with Autoware, which is an open-source self-driving system. This cooperation facilitates testing the self-driving systems. This framework can help developers create scenarios.