Adaptive Decision-Making for Intelligent Driving Systems Based on Multimodal Psychological Emotion Recognition
Zili Chen, Aihong Liu, Shubo Zhang, Zhangjie YuanAbstract
Objective
Long-term driving brings heavy psychological pressure to drivers. Mental states become unstable easily. Mental health is threatened. Driving safety is affected indirectly. This study designs an adaptive decision-making intelligent driving system based on multimodal psychological emotion recognition. It aims to alleviate drivers’ psychological burden. It protects drivers’ mental health. It reduces safety risks caused by poor mental states. It promotes humanized driving and ensures driving safety.
Subjects and Methods
This study selects drivers with different driving experiences as subjects. It adopts multimodal recognition technology. It collects facial expressions and physiological signals of drivers. It captures psychological emotion data accurately. It uses data analysis methods. It explores the correlation between drivers’ mental states and driving safety. It focuses on the impact of psychological pressure on driving behavior. It provides a basis for system optimization.
Results
The adaptive intelligent driving system identifies negative emotions accurately. It adjusts driving modes according to drivers’ mental states. It relieves drivers’ psychological tension effectively. It stabilizes drivers’ mental states. It reduces the impact of poor mental health on driving quality. It lowers safety risks. It improves driving adaptability. It protects drivers’ mental health and enhances driving experience.
Conclusions
Multimodal psychological emotion recognition is key to optimizing intelligent driving systems. The adaptive decision-making function meets drivers’ psychological needs. It alleviates psychological pressure. It stabilizes mental states. It protects drivers’ mental health. It provides technical support for safe and humanized driving. It promotes the high-quality development of intelligent driving.
Acknowledgement
This research was supported by 1. 2025 Ministry of Education Vocational College Informatization Teaching Steering Committee National Higher Vocational College Artificial Intelligence General Education Course Teaching Research Project: Research on the Evaluation of AI General Education Courses in Higher Vocational Colleges Based on Ecosystem Theory (Project No. KT2508039). 2. 2025 Chongqing Vocational Education Teaching Reform Key Research Project: Research on the Reform and Practice of AI-Enabled Vocational Education Classroom Teaching Models (Project No. Z2252062).
Corresponding Author
Aihong Liu, Chongqing Creation Vocational College, Chongqing 402160, China.