CN112130563B - A multi-objective screening assisted driving control method - Google Patents

Abstract

The invention discloses a multi-target screening assisted driving control method, which includes: acquiring data information in front of a main vehicle; generating a central trajectory curve equation of the main vehicle; ; Determine whether the target object is in the dangerous area set by the host vehicle, and if so, judge it as a dangerous target; obtain and output the longitudinal distance between the dangerous target and the host vehicle. Based on multi-sensor information, the invention proposes a new control method for obtaining the recommended target, which improves the accuracy and reliability of target screening during the day and night.

Description

A multi-objective screening assisted driving control method

technical field

The invention belongs to the technical field of target screening for multi-vehicle automatic driving, relates to an intelligent driving vehicle auxiliary driving method, and in particular relates to a multi-target screening auxiliary driving control method and system.

Background technique

With the rapid development of modern society and economy, people's material needs continue to increase. As a tool to liberate people from tedious manual operations, smart vehicles have attracted more and more attention from enterprises. As an important part of the interaction between the vehicle and the environment, the intelligent vehicle environment perception layer identifies the environment and state of the vehicle through sensor technology, and provides reliable data for the decision-making planning layer. When a single sensor is used for perceptual detection, there are always problems of low accuracy and poor stability.

Invention content:

In order to overcome the defects of the above-mentioned background technology, the present invention provides a multi-target screening assisted driving control method, which improves the accuracy and reliability of target screening during the day and night.

In order to solve the above-mentioned technical problems, the adopted technical scheme of the present invention is:

A multi-objective screening assisted driving control method, comprising:

Step 1, obtain the data information in front of the main vehicle;

Step 2, generate the center trajectory curve equation of the main vehicle;

Step 3, in combination with the data information in front of the main vehicle, obtain the DTC of the shortest distance between the target object and the central trajectory line of the main vehicle;

Step 4, determine whether the target object is in the dangerous area set by the host vehicle, if so, it is determined as a dangerous target;

Step 5: Obtain and output the longitudinal distance between the dangerous target and the host vehicle.

Preferably, in step 1, the data information in front of the main vehicle is acquired through multiple sensors, and the multiple sensors include millimeter-wave radar, cameras, and infrared sensors.

Preferably, the data information in front of the vehicle includes the selected target ID of the vehicle in front of the host vehicle in the left, middle and right lanes, the longitudinal distance of the selected target, the relative speed of the selected target, the deflection angle of the left corner of the selected target, and the right corner of the selected target. Declination, lane line information.

Preferably, the main vehicle center trajectory curve equation

i＝1,2,3分别为左中右三个车道左边的车道线轨迹曲线方程；

i＝1,2,3 分别为左中右三个车道右边的车道线轨迹曲线方程。Among them, C _i , i=1, 2, 3 are respectively the center trajectory curves of the three lanes of the left, center, and right of the main vehicle;

i=1, 2, 3 are the lane line trajectory curve equations on the left side of the left, center, and right lanes respectively;

i=1, 2, 3 are the lane line trajectory curve equations on the right side of the left, center, and right lanes, respectively.

Preferably, the shortest distance between the target object and the center track line of the main vehicle

DTC=|L sinβ-f(L cosβ)|·cos(arctan[f(L cosβ)])

Among them, the shortest distance between the target vehicle and the main vehicle is L, the declination angle is β, the equation of the center line of the main vehicle is f(), and the equation of the center line of the main vehicle is f'().

The beneficial effect of the present invention is that: the sensor detects the specific position information and motion state of the multi-target vehicle (or pedestrian) sent in front of the host vehicle. According to the multi-target parameter values and the actual lane conditions, a dangerous target area with a certain boundary range is delineated. The boundary of the dangerous area can be adjusted according to the position and motion information of the target object. Based on multi-sensor information, the invention proposes a new control method for obtaining the recommended target, which improves the accuracy and reliability of target screening during the day and night.

Description of drawings

1 is a flow chart of a method according to an embodiment of the present invention;

2 is a schematic diagram of a dangerous target area according to an embodiment of the present invention;

3 is a schematic diagram of a system configuration according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of the shortest distance between the target object and the center track of the host vehicle according to an embodiment of the present invention.

Detailed ways

The present invention will be further described below with reference to the accompanying drawings and embodiments.

The invention relates to a method for screening multiple forward-emitting objects based on radar, camera, infrared and the like in the field of automatic driving, and realizes the screening and tracking of forward-emitting multiple vehicles. As shown in Figure 1, the multi-target screening method provided in this embodiment includes the following steps:

Use including but not limited to millimeter-wave radar, camera and infrared to obtain data information ahead (three-lane vehicles in front of the main vehicle, left, middle, and right), including the ID of the selected target (ID is the number calibrated by the internal calculation of the sensor), the longitudinal direction of the selected target Distance (the longitudinal distance between the target and the main vehicle), relative speed of the selected target (the speed of the target relative to the speed of the main vehicle), the left corner angle of the selected target, the right corner angle of the selected target, and lane line information ( quality, curvature of the lane lines), etc.

In the camera coordinate system, when the target is on the left side of the main vehicle, it is considered that its right corner declination Right_Angle is the declination value of the point where the target is closest to the main vehicle; if the target is on the right side of the main vehicle, It is considered that its left corner point declination Left_Angle is the declination value of the point where the target is closest to the main vehicle.

When there is no lane line or the quality of the lane line is poor, the parameter value is 0; when only one side of the lane line is of good quality, the parameter of the lane line on that side is used as the parameter of the center trajectory curve equation of the main vehicle, and the parameter value of the constant term is 0; When the quality of the side lane lines is good, the center trajectory curve equation of the main vehicle can be approximated by the following averaging method in the camera coordinate system:

C ₀ =0

Calculate the center trajectory curve equation C of the host vehicle in the sensor coordinate system.

i＝1,2,3代表左中右三个车道左边的车道线轨迹曲线方程；

i＝1,2,3代表左中右三个车道右边的车道线轨迹曲线方程；In the equation: Ci, i=1, 2, 3 represent the center trajectory curve of the left, middle, and right lanes of the host vehicle;

i=1,2,3 represents the lane line trajectory curve equation on the left side of the left, center, and right lanes;

i=1, 2, 3 represents the lane line trajectory curve equation on the right side of the left, middle, and right lanes;

Combined with the state information of the vehicle ahead detected by the sensor, the DTC of the closest distance between the target and the center trajectory of the main vehicle can be calculated;

The closest distance value of the target object to the center trajectory of the main vehicle is shown in Figure 4. Point S is the closest point between the target object and the main vehicle, and the included angle is β; point A is the intersection of the horizontal line from point S and the central trajectory line of the main vehicle; point B is the vertical line from point S to the central trajectory line of the main vehicle. foot. The angle α is the angle between the tangent line passing through point A and the longitudinal axis, which can be used to approximate the angle between the two line segments SA and SB. The distance represented by the line segment SB in the figure is the shortest distance between the target and the center track of the main vehicle to be calculated.

Assuming that the equation of the center line of the host vehicle is f(x), the shortest distance between the target vehicle and the host vehicle is L, and the declination angle is β, the calculation method of the distance DTC between the target object and the center trajectory line of the host vehicle can be approximated by the following formula.

DTC=|L sinβ-f(L cosβ)||·cos(afctan[f'(L cosβ)])

Combined with the actual lane line information, the vertical distance of the multi-target objects from the center track of the main vehicle and the relative lateral movement speed, a dangerous target area is determined (the decision method is shown in the triangle and quadrilateral areas in Figure 2), as long as the target objects are in their respective In the corresponding dangerous target area, the target is considered as a dangerous target, and the longitudinal distance of all dangerous targets from the host vehicle is output downward (target screening module).

According to the actual road conditions and sensor characteristics, the structure of the selected hazardous target area is shown in the area of Fig. 2. This area can be regarded as a left-right symmetrical combination of the triangular area ABE and the quadrilateral area BCDE after splicing.

The boundary parameters of the hazardous area mainly include the following five parameters:

L1: The value of the longitudinal distance between the boundary of the dangerous target area and the closest point to the main vehicle;

L2: The value of the longitudinal distance from the widest part of the dangerous target area to the main vehicle;

L3: The longitudinal distance from the boundary of the dangerous target area to the farthest distance from the main vehicle;

D1: the lateral width at the position of the dangerous target area L1;

D2: The lateral width at the L2 position of the dangerous target area.

If the above parameters are given appropriate initial values, the dangerous target can be obtained, and the longitudinal distance of all dangerous targets SA_Object from the main vehicle can be output. Then compare the longitudinal relative distance with the dangerous target CIPV_Object recommended by the sensor, and select the final tracking target Dobj.

It should be understood that, for those skilled in the art, improvements or changes can be made according to the above description, and all these improvements and changes should fall within the protection scope of the appended claims of the present invention.

Claims (3)

1. A multi-target screening assisted driving control method is characterized by comprising the following steps:

step 1, acquiring data information in front of a main vehicle;

step 2, generating a curve equation of the central track of the main vehicle;

step 3, acquiring the closest distance DTC between the target object and the central trajectory of the main vehicle by combining the front data information of the main vehicle; determining a dangerous target area by combining actual lane line information, vertical distances between the multiple targets and the central track of the main vehicle and lateral relative movement speeds, regarding the target as a dangerous target as long as the target is in the dangerous target area corresponding to each target, and outputting longitudinal distances between all dangerous targets and the main vehicle to a target screening module;

step 4, judging whether the target object is in a dangerous area set by the main vehicle, and if so, judging the target object as a dangerous target;

step 5, acquiring and outputting the longitudinal distance between the dangerous target and the main vehicle; the method comprises the following steps that 1, data information in front of the main vehicle is obtained through multiple sensors, wherein the multiple sensors comprise a millimeter wave radar, a camera and an infrared sensor;

curve equation of central track of the main vehicle

Wherein, C_iI is 1,2 and 3 are respectively the central track curves of the left, the middle and the right lanes of the main vehicle

The lines, i is 1,2,3 are lane line track curves on the left of the left, middle and right three lanesA line equation;

respectively are lane line track curve equations on the right of the left, middle and right three lanes.

2. The multi-target screening assisted driving control method according to claim 1, characterized in that: the vehicle front data information comprises the ID of a selected target object, the longitudinal distance of the selected target object, the relative speed of the selected target object, the left corner deviation angle of the selected target object, the right corner deviation angle of the selected target object and lane line information of a vehicle in the left, middle and right three lanes in front of the main vehicle.

3. The multi-target screening assisted driving control method according to claim 1, characterized in that: the closest distance of the target object to the central trajectory line of the main vehicle

DTC＝|L sinβ-f(L cosβ)|·cos(arctan[f′(L cosβ)])

Wherein, the shortest distance between the target vehicle and the main vehicle is L, the deflection angle is beta, the equation of the central line of the main vehicle is f (), and the equation of the central line of the main vehicle is f' ().

Images