Online trajectory prediction method based on particle filtering

A trajectory prediction and particle filter technology, which is applied in complex mathematical operations, biological neural network models, neural architectures, etc., can solve the problems of dynamic modeling of trajectory prediction models, strong nonlinearity of the system, and unsatisfactory states, and achieve online solutions. Effects of updated questions, simple structure, and improved accuracy

CN111159642AActive Publication Date: 2020-05-15NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
5 Cites 6 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2020-05-15

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

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.
Need to check novelty before this filing date? Find Prior Art

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 ...

Examples

Embodiment Construction

[0044] In order to facilitate the understanding of those skilled in the art, the present invention will be further described below in conjunction with the embodiments and accompanying drawings, and the contents mentioned in the embodiments are not intended to limit the present invention.

[0045] refer to figure 1 As shown, a kind of online trajectory prediction method based on particle filter of the present invention, comprises steps as follows:

[0046] 1) Establish a trajectory prediction model based on the gated cyclic unit, take the longitudinal position x, lateral position y, vehicle speed v and acceleration a of the historical time domain [-T, 0] as input, and output the future time domain [0, T] Longitudinal position x, lateral position y and vehicle speed v;

[0047] refer to image 3 As shown, the gated recurrent unit is a variant of the recurrent neural network. While solving the gradient explosion problem in the training process, the structure is simpler than the...