Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Target trajectory prediction method based on Kalman filtering multi-motion model switching

A Kalman filter and target trajectory technology, applied in complex mathematical operations, image data processing, instruments, etc., can solve problems such as unsatisfactory motion model tracking effects, avoid storage and synchronous calculation iterations, and improve estimation accuracy.

Pending Publication Date: 2021-12-07
DONGFENG MOTOR GRP
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] As the basic algorithm of sensor target tracking, the Kalman filter can calculate the optimal estimate of the target state according to the input measurement of the sensor. The motion models commonly used in the prediction of the Kalman filter include CV, CA, CTRV, and CTRA. The first two One is a linear model, and the latter two are nonlinear models. Kalman filtering is only suitable for linear models. For nonlinear models, extended Kalman is generally used. For maneuvering target tracking, due to the uncertainty of its motion state, a single Motion model tracking is not ideal

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Target trajectory prediction method based on Kalman filtering multi-motion model switching
  • Target trajectory prediction method based on Kalman filtering multi-motion model switching
  • Target trajectory prediction method based on Kalman filtering multi-motion model switching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0153] Take the target vehicle detected by the millimeter-wave radar when the own vehicle changes lanes as an example:

[0154] like Figure 4 As shown, within 7s, 0~2s is decelerating straight, 2~5s is uniform lane change, 5s~7s is accelerating straight, the real trajectory of the target is a black line, and the millimeter wave radar observation trajectory Z(k) is a point shape:

[0155] 1. Establish a target tracking model based on the Kalman multi-motion model, assuming no parameter noise:

[0156]

[0157] p(k|k-1)=A i p(k-1|k-1)A i T +Q(k)

[0158] K=p(k|k-1)H T (Hp(k|k-1)H T +R) -1

[0159]

[0160] p(k|k)=p(k|k-1)-KHp(k|k-1)

[0161] in:

[0162]

[0163] i={1, 2, 3}

[0164]

[0165]

[0166] in:

[0167]

[0168]

[0169] (v y ', v x ' is the state value of the previous frame)

[0170] 2, model switching,

[0171] According to the scene, this period of time is divided into three stages, the early deceleration stage, the middle la...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a target trajectory prediction method based on Kalman filtering multi-motion model switching. The method comprises the following steps: establishing a Kalman filtering multi-motion model; collecting motion information of the target in a period of time during a motion period, wherein the motion information at least comprises a target initial coordinate, a target real-time speed and a target real-time acceleration; obtaining the motion state of the target according to the motion information of the target, and switching the Kalman filtering motion model according to the change of the motion state, wherein the motion state at least comprises deceleration straight movement, constant-speed straight movement, acceleration straight movement, deceleration lane changing, constant-speed lane changing and acceleration lane changing; and substituting the motion information of the target into different Kalman filtering motion models which are switched according to the motion state change, and calculating to obtain a prediction track of the target. According to the invention, the target is tracked by using the multi-motion model, and the estimation precision of the filter is improved.

Description

technical field [0001] The invention belongs to the technical field of trajectory prediction, and in particular relates to a target trajectory prediction method based on Kalman filtering multi-motion model switching. Background technique [0002] As the basic algorithm of sensor target tracking, the Kalman filter can calculate the optimal estimation of the target state according to the input measurement of the sensor. The commonly used motion models in the prediction of Kalman filter include CV, CA, CTRV, and CTRA. One is a linear model, and the last two are nonlinear models. Kalman filtering is only suitable for linear models. For nonlinear models, extended Kalman is generally used. For maneuvering target tracking, due to the uncertainty of its motion state, a single Motion model tracking is not ideal. SUMMARY OF THE INVENTION [0003] The purpose of the present invention is to provide a target trajectory prediction method based on Kalman filtering multi-motion model swi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/277G06T7/20G06F17/16G06F17/11
CPCG06T7/277G06T7/20G06F17/11G06F17/16
Inventor 熊盼盼余昊严义雄庹新娟
Owner DONGFENG MOTOR GRP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products