Vehicle driving risk prediction method based on time varying state transition probability markov chain

Abstract

The invention provides a vehicle driving risk prediction method based on time varying state transition probability markov chain. Firstly, an offline vehicle driving risk prediction model training: based on samples of accidents and near accidents, real-time vehicle driving risk states are divided by clustering time window characteristics parameters and regarded as countable states of the markov chain, and a multiterm logistic model of vehicle driving risk states transition in different vehicle driving risk states is built. Secondly, an online vehicle driving risk model real-time prediction: under the circumstance of car networking, the variable parameters required by a prediction model are collected in real time, through a risk state clustering center position and markov property, an original state probability distribution vector and a markov chain n steps transition probability at any time in the future are calculated, and the prediction result of the vehicle risk states in the futureis obtained. According to the invention, by means of a recurrence algorithm, the estimation of markov chain n steps time varying state transition probability is achieved, which can reflect the characteristics of the vehicle driving risk states changing with the characteristics of the transportation system, and can meet the requirement of early warning in real time.

Description

technical field [0001] The invention relates to the technical field of traffic safety evaluation and intelligent traffic system active safety, in particular to a driving risk prediction method based on a time-varying state transition probability Markov chain. Background technique [0002] On the basis of the perception of the running state of the vehicle and surrounding vehicles, research and prediction of the future driving risk state of the vehicle will help to achieve an accurate and timely collision warning or intervention mechanism for the assisted driving system. At present, the early warning of driving risk mainly calculates the selected early warning variables in real time and compares them with the preset risk thresholds of different levels. Among them, the widely used early warning variables mainly include collision time, inter-vehicle time and distance. In fact, it is difficult to describe the entire process from the formation of driving risks to the occurrence of...

AI Technical Summary

Problems solved by technology

In fact, the entire process from the formation of driving risks to the occurrence of dangerous conflicts is difficult to describe with a single early warning parameter, and more complex models and algorithms are needed for research

However, the current early warning model algorithms at home and abroad usually only consider the operating characteristics of vehicles (such as inter-vehicle distance, speed and acceleration characteristics, etc.), while ignoring the impact of dynamic driver behavior, road and environmental changes on the driving risk state, and cannot fully reflect the driving characteristics. The internal evolution law between states is not conducive to the accuracy and prediction accuracy of the driving risk model

Images