Jing Huang , Tingnan Liu , Yezi Hu , Zhipeng He , Lin Hu
{"title":"Assessment and recognition of driver situation awareness in conditional autonomous driving: Integrating cognitive psychology and machine learning","authors":"Jing Huang , Tingnan Liu , Yezi Hu , Zhipeng He , Lin Hu","doi":"10.1016/j.jii.2025.100894","DOIUrl":null,"url":null,"abstract":"<div><div>Driver Situation Awareness (SA) is crucial for the safety of conditional autonomous driving, posing a significant human factors challenge for the automotive industry in its pursuit of intelligent driving systems. To guide future automotive system design and enhance Human–Machine Interaction (HMI), the present paper presents an interdisciplinary solution that achieves the assessment and recognition of driver SA by deeply integrating cognitive psychology theories and machine learning techniques. First, a takeover driving study was designed and conducted during the conditional autonomous driving phase. Various physiological and behavioral data were collected, along with information from measurement questionnaires. Next, a driver quantitative SA model was developed based on ACT-R and the actual allocation of the driver’s visual attention, accounting for both goal-directed and data-directed processing. For a comprehensive SA assessment, the results from this model and the questionnaires were combined and integrated as composite features. Using the K-means clustering algorithm and the silhouette coefficient method, the assessment of driver SA is achieved by clustering driver SA into two levels: low SA and high SA, overcoming the limitations of single information sources. Furthermore, by fusing physiological and behavioral data as well as visual attention levels as multimodal features, machine learning classifiers were employed for real-time recognition of driver SA, achieving the highest Accuracy of 93.29%. Finally, the validity of the experimental design was confirmed through RM-ANOVA analysis of the experimental conditions and SA indicators, and the effectiveness of the quantitative model was validated via correlation analysis between the model’s results and questionnaire outcomes. This research provides an innovative solution for driver SA assessment and recognition, offering valuable insights for developing safer HMI in intelligent vehicles and advancing industrial information integration within the automotive sector.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"47 ","pages":"Article 100894"},"PeriodicalIF":10.4000,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Industrial Information Integration","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2452414X25001177","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
Driver Situation Awareness (SA) is crucial for the safety of conditional autonomous driving, posing a significant human factors challenge for the automotive industry in its pursuit of intelligent driving systems. To guide future automotive system design and enhance Human–Machine Interaction (HMI), the present paper presents an interdisciplinary solution that achieves the assessment and recognition of driver SA by deeply integrating cognitive psychology theories and machine learning techniques. First, a takeover driving study was designed and conducted during the conditional autonomous driving phase. Various physiological and behavioral data were collected, along with information from measurement questionnaires. Next, a driver quantitative SA model was developed based on ACT-R and the actual allocation of the driver’s visual attention, accounting for both goal-directed and data-directed processing. For a comprehensive SA assessment, the results from this model and the questionnaires were combined and integrated as composite features. Using the K-means clustering algorithm and the silhouette coefficient method, the assessment of driver SA is achieved by clustering driver SA into two levels: low SA and high SA, overcoming the limitations of single information sources. Furthermore, by fusing physiological and behavioral data as well as visual attention levels as multimodal features, machine learning classifiers were employed for real-time recognition of driver SA, achieving the highest Accuracy of 93.29%. Finally, the validity of the experimental design was confirmed through RM-ANOVA analysis of the experimental conditions and SA indicators, and the effectiveness of the quantitative model was validated via correlation analysis between the model’s results and questionnaire outcomes. This research provides an innovative solution for driver SA assessment and recognition, offering valuable insights for developing safer HMI in intelligent vehicles and advancing industrial information integration within the automotive sector.
期刊介绍:
The Journal of Industrial Information Integration focuses on the industry's transition towards industrial integration and informatization, covering not only hardware and software but also information integration. It serves as a platform for promoting advances in industrial information integration, addressing challenges, issues, and solutions in an interdisciplinary forum for researchers, practitioners, and policy makers.
The Journal of Industrial Information Integration welcomes papers on foundational, technical, and practical aspects of industrial information integration, emphasizing the complex and cross-disciplinary topics that arise in industrial integration. Techniques from mathematical science, computer science, computer engineering, electrical and electronic engineering, manufacturing engineering, and engineering management are crucial in this context.