Online trajectory prediction method based on particle filtering

Abstract

The invention discloses an online trajectory prediction method based on particle filtering. The method comprises the steps: 1) building a trajectory prediction model, taking a longitudinal position x,a lateral position y, a vehicle speed v and an acceleration a of a historical time domain [-T, 0] as the input, and outputting the longitudinal position x, the lateral position y and the vehicle speed v of a future time domain [0, T]; and 2) correcting and updating the state of the trajectory prediction model by using the current measurement quantity. When the track is predicted, the informationof one time sequence can be input, the influence of the information of the previous moment on the information of the next moment is considered, and the prediction accuracy of the model in the dynamicenvironment is improved; in a nonlinear system in the presence of interference and noise, a statistical method is used to solve the prediction filtering problem, and an accurate solution of a state can be approached.

Description

technical field [0001] The invention belongs to the technical field of intelligent driving, and specifically refers to an online trajectory prediction method based on particle filtering. Background technique [0002] With the increasing number of cars, road traffic tends to be denser and more complicated, which leads to an increase in driving pressure, which reduces the driving ability of drivers in normal traffic scenarios and greatly increases the probability of traffic accidents. In the decision-making process of intelligent driving, the correct prediction of the trajectory of surrounding vehicles is the basis for intelligent vehicles to make appropriate decisions. [0003] At present, intelligent vehicles can use advanced technology to predict the future state according to the movement state of the target vehicle, and plan the driving route of the vehicle based on this information. Most of the methods used in current technology rely on information at a certain moment to ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of the above-mentioned prior art, the object of the present invention is to provide an online trajectory prediction system and method based on particle filter, to solve the dynamic modeling of the trajectory prediction model and the strong system dynamics that are difficult to solve by traditional methods in the prior art. Non-linear, and its state does not necessarily meet the problem of filtering in the case of Gaussian distribution

Images