You Ren, Xiyao Wang, Jiaqi Song, Wenyang Lu, Penglong Li, Shangke Li
{"title":"Driving Intention Recognition Model for Highway Ramp-Merging\u0000 Scene","authors":"You Ren, Xiyao Wang, Jiaqi Song, Wenyang Lu, Penglong Li, Shangke Li","doi":"10.4271/12-08-02-0016","DOIUrl":"https://doi.org/10.4271/12-08-02-0016","url":null,"abstract":"Driving safety in the mixed traffic state of autonomous vehicles and conventional\u0000 vehicles has always been an important research topic, especially on highways\u0000 where autonomous driving technology is being more widely adopted. The merging\u0000 scenario at highway ramps poses high risks with frequent vehicle conflicts,\u0000 often stemming from misperceived intentions [1].\u0000\u0000 \u0000This study focuses on autonomous and conventional vehicles in merging scenarios,\u0000 where timely recognition of lane-changing intentions can enhance merging\u0000 efficiency and reduce accidents. First, trajectory data of merging vehicles and\u0000 their conflicting vehicles were extracted from the NGSIM open-source database in\u0000 the I-80 section. The segmented cubic polynomial interpolation method and\u0000 Savitzky–Golay filtering are utilized for data outlier removal and noise\u0000 reduction. Second, the processed trajectory data were used as input to a hybrid\u0000 Gaussian hidden Markov (GMM-HMM) model for driving intention classification,\u0000 specifically lane-change collision-avoidance and lane keeping. The K-means\u0000 algorithm is used to initialize the model parameters, and the\u0000 expectation–maximization (EM) algorithm is employed for parameter iteration.\u0000 Finally, through validation on the testing set, the mixed Gaussian hidden Markov\u0000 model achieves a lane-change intention recognition accuracy of over 95% for\u0000 conflicting vehicles and outperforms the support vector machines (SVM) model and\u0000 the long–short-term memory (LSTM) network. It can be applied to the humanized\u0000 design of intelligent vehicle lane-change strategies, effectively reducing\u0000 lane-change risks and improving driving safety.","PeriodicalId":487149,"journal":{"name":"SAE international journal of connected and automated vehicles","volume":"49 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141808870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}