Every year, many people are killed and injured in highway traffic accidents.In order to reduce such casualties, collisions warning systems has been studiedextensively. These systems are built by taking the driver reaction times intoaccount. However, most of the existing literature focuses on characterizing howdriver reaction times vary across an entire population. Therefore, many of thewarnings that are given turn out to be false alarms. A false alarm occurswhenever a warning is sent, but it is not needed. This would nagate any safetybenefit of the system, and could even reduce the overall safety if warningsbecome a distraction. In this paper, we propose our solution to address thedescribed problem; First, we briefly describe our method for estimating thedistribution of brake response times for a particular driver using data from aVehicular Ad-Hoc Network (VANET) system. Then, we investigate how brakeresponse times of individual drivers can be used in collision warningalgorithms to reduce false alarm rates while still maintaining a high level ofsafety. This will yield a system that is overall more reliable and trustworthyfor drivers, which could lead to wider adoption and applicability for V2V/V2Icommunication systems. Moreover, we show how false alarm rate varies withrespect to probability of accident. Our simulation results show that byindividualizing collision warnings the number of false alarms can be reducedmore than $50\%$. Then, we conclude safety applications could potentially takefull advantage of being customized to an individual's characteristics.
展开▼
