Driving intention determination method and device

Abstract

The invention discloses a driving intention determination method and device and belongs to the traffic technology field. The method comprises the following steps of acquiring the state information oftraffic targets in a driving environment, wherein the traffic targets include a traffic target in a moving state and a traffic target in a static state, and the state information of the static-state traffic target at least includes the indication information of a traffic identification and road boundary information; determining the risk field of the driving environment based on the state information of the traffic targets in the driving environment; for any other vehicle in the driving environment, determining the running tracks of the other vehicles in the driving environment based on the risk field; and determining the driving intentions of the other vehicles based on the running tracks of the other vehicles in the driving environment. In the invention, a driving intention determinationprocess can be simplified, the driving intention determination efficiency and accuracy of the other vehicles are increased, then, a determination basis can be provided for the reasonable decision andcontrol of the vehicles and the active safety of the vehicles is increased.

Description

technical field [0001] The present application relates to the field of traffic technology, in particular to a method and device for determining driving intention. Background technique [0002] With the rapid development of unmanned driving technology and driving assistance systems, in order to improve the safety of unmanned vehicles or vehicles using driving assistance systems during driving, it is often necessary to monitor other vehicles in the driving environment where the vehicle is located. The driving intention is predicted so that a reasonable and safe decision-making control can be performed on the vehicle according to the driving intention of other vehicles. The driving intention may include changing lanes left, changing lanes right, driving straight, etc. [0003] Currently, a method for determining driving intention based on a Bayesian network is provided. Specifically, for each other vehicle in the driving environment, the vehicle respectively establishes a Baye...

AI Technical Summary

Problems solved by technology

[0004] However, the conditional probability distribution among the nodes in the Bayesian network model is often difficult to obtain accurately, which will lead to the low accuracy of the intention prediction results of the Bayesian network model in the above method, which will lead to subsequent determination based on the intention prediction results. Accuracy of driving intentions is low

In addition, if the driving intentions of multiple other vehicles need to be determined, three independent Bayesian network models need to be established for the multiple other vehicles in the above method. In this case, the driving intentions of the multiple other vehicles The determination process is very cumbersome and the determination efficiency is low

Images