Decision-Making and Planning for Intelligent Vehicle Considering Human Factors: Methods, Challenges, and Prospects

The existing research on intelligent driving vehicles mainly focuses on improving the performance of safety, economy, and control accuracy, ignoring the personalized manipulation pReferences of different driving groups. The differences in driving styles and preferences of different passengers require that the driving behavior of intelligent driving systems in different traffic situations should conform to the habits of self-vehicle passengers, that is, to achieve personalized driving considering human factors. This paper provides a comprehensive and systematic review of the research status in the field of personalized driving. Firstly, it clarifies the necessity of personalized driving. Secondly, the existing decision-making and planning methods for personalized driving of single-vehicle are summarized from two aspects: machine learning-based methods and driver characteristic characterization-based methods. On this basis, the interactive decision-making and planning method of multi-vehicle games considering personalized preference in intelligent networking and mixed driving environments is summarized. Finally, the problems faced by the research of personalized intelligent driving systems and the future development trend are analyzed and prospected.