It is well known that not all drivers drive the same and that the same driver has different driving characteristics with different vehicles. Identifying the characteristics that are unique to each driver/vehicle response opens the way for more personalized and accurate driver assistance systems. In this paper, we consider the problem of identifying the driver/vehicle characteristics by processing real-time driving response data. We propose the use of a Gaussian mixture model combined with the knowledge of dynamic characteristics modeled as probability distributions together with additional logic and appropriate thresholds in order to implement a real-time driver/vehicle response diagnostics system. We focus our efforts on the vehicle-following part of driving. The system is tested on a customized vehicle using different drivers under different driving conditions. We demonstrated that the system can distinguish between different drivers and can classify driver aggressiveness during vehicle following.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.