{"title":"自动驾驶汽车的多阶段变道决策方法","authors":"Lei Cai, Hsin Guan, Qi Hong Xu, Xin Jia, Jun Zhan","doi":"10.1177/09544070241265401","DOIUrl":null,"url":null,"abstract":"Lane changing is one of the common behaviors in urban and highway scenarios. Therefore, lane-changing behavior is very important in autonomous driving decisions. First, lane change (LC) decisions are divided into waiting to LC, overtaking, LC, and returning to the original lane (RTOL). The LC can be divided into a lane change preparation phase (LCPP), a lane change execution phase (LCEP) 1, and a LCEP 2. The driving intention during the LCPP is further determined by determining the optimal longitudinal acceleration during the LCPP. Second, the conditions under which the host vehicle (HV) chooses to overtake, wait to LC, and choose to LC are proposed, that is, a method for determining the choice of different LC driving options. A condition is proposed for HV to give up overtaking. Third, the practice of determining the interaction process between the host and rear vehicles based on the potential conflict area (PCA) is proposed in LCEP 1. The interaction between the two cars is constructed using a dynamic game method. Finally, VTD (Virtual Test Drive) simulates and verifies the proposed LC decision system.","PeriodicalId":54568,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers Part D-Journal of Automobile Engineering","volume":"45 1","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2024-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A multi-phase lane change decision-making method for autonomous vehicles\",\"authors\":\"Lei Cai, Hsin Guan, Qi Hong Xu, Xin Jia, Jun Zhan\",\"doi\":\"10.1177/09544070241265401\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Lane changing is one of the common behaviors in urban and highway scenarios. Therefore, lane-changing behavior is very important in autonomous driving decisions. First, lane change (LC) decisions are divided into waiting to LC, overtaking, LC, and returning to the original lane (RTOL). The LC can be divided into a lane change preparation phase (LCPP), a lane change execution phase (LCEP) 1, and a LCEP 2. The driving intention during the LCPP is further determined by determining the optimal longitudinal acceleration during the LCPP. Second, the conditions under which the host vehicle (HV) chooses to overtake, wait to LC, and choose to LC are proposed, that is, a method for determining the choice of different LC driving options. A condition is proposed for HV to give up overtaking. Third, the practice of determining the interaction process between the host and rear vehicles based on the potential conflict area (PCA) is proposed in LCEP 1. The interaction between the two cars is constructed using a dynamic game method. Finally, VTD (Virtual Test Drive) simulates and verifies the proposed LC decision system.\",\"PeriodicalId\":54568,\"journal\":{\"name\":\"Proceedings of the Institution of Mechanical Engineers Part D-Journal of Automobile Engineering\",\"volume\":\"45 1\",\"pages\":\"\"},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2024-08-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Institution of Mechanical Engineers Part D-Journal of Automobile Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1177/09544070241265401\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, MECHANICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Institution of Mechanical Engineers Part D-Journal of Automobile Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1177/09544070241265401","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
A multi-phase lane change decision-making method for autonomous vehicles
Lane changing is one of the common behaviors in urban and highway scenarios. Therefore, lane-changing behavior is very important in autonomous driving decisions. First, lane change (LC) decisions are divided into waiting to LC, overtaking, LC, and returning to the original lane (RTOL). The LC can be divided into a lane change preparation phase (LCPP), a lane change execution phase (LCEP) 1, and a LCEP 2. The driving intention during the LCPP is further determined by determining the optimal longitudinal acceleration during the LCPP. Second, the conditions under which the host vehicle (HV) chooses to overtake, wait to LC, and choose to LC are proposed, that is, a method for determining the choice of different LC driving options. A condition is proposed for HV to give up overtaking. Third, the practice of determining the interaction process between the host and rear vehicles based on the potential conflict area (PCA) is proposed in LCEP 1. The interaction between the two cars is constructed using a dynamic game method. Finally, VTD (Virtual Test Drive) simulates and verifies the proposed LC decision system.
期刊介绍:
The Journal of Automobile Engineering is an established, high quality multi-disciplinary journal which publishes the very best peer-reviewed science and engineering in the field.