Front target merging cut-in prediction method and device, electronic equipment and storage medium

Abstract

The application relates to the technical field of decision planning of vehicles, in particular to a front target confluence cut-in prediction method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring position information of a current vehicle, and determining a target cut-in vehicle according to the position information of the current vehicle; acquiring a plurality of interactive vehicles of the target cut-in vehicle in the same lane and adjacent lanes, and calculating a confluence posture coefficient sum of the plurality of interactive vehicles in a confluence posture; when the target cut-in vehicle is in the confluence posture and the confluence posture coefficient sum is greater than a preset value, calculating a lateral position prediction value of the target cut-in vehicle, and predicting whether the target cut-in vehicle flows into a lane where the current vehicle is located according to the prediction value. According to the front target confluence cut-in prediction method, early prediction is made by recognizing a front confluence target vehicle, so that the vehicle can be helped to plan a deceleration in advance and perform a braking action, thereby avoiding a collision with a front vehicle, and the safety and driving comfort are improved.

Description

Technical Field

[0001] This application relates to the field of vehicle decision-making and planning technology, and in particular to a method, device, electronic device and storage medium for predicting the convergence and entry of a target ahead. Background Technology

[0002] Autonomous driving technology mainly comprises three parts: environmental perception, decision-making and planning, and control execution. With the continuous development of autonomous driving, the requirements for autonomous driving functions in urban areas are gradually increasing, which also places higher demands on the decision-making and planning capabilities of autonomous vehicles. To improve the decision-making and planning capabilities of vehicles on urban roads and urban expressways without high-precision map coverage, it is necessary to identify and predict the behavior of other targets around the vehicle, especially forward merging targets, to ensure the rationality and anticipation of decision-making and planning, and to reserve sufficient processing time for the control execution part to improve driving safety and comfort.

[0003] Among related technologies, there are three main methods for identifying confluence targets:

[0004] (1) Based on a high-precision map or ADAS (Advanced Driver Assistance System) map, the vehicle's position on the map output by the positioning module is used to detect whether the vehicle is in the merging area, thereby identifying the merging target.

[0005] (2) Based on the camera, the image detection device detects that there is an entrance or exit in front of the road, thereby identifying the merging target.

[0006] (3) Based on V2X (vehicle to everything), the central controller identifies whether a vehicle has entered the merging area based on the real-time information of the intelligent connected vehicle, thereby identifying the merging target.

[0007] However, the above-mentioned confluence target identification method has the following drawbacks:

[0008] (1) It requires autonomous vehicles to be equipped with high-precision maps or ADAS maps, and the vehicles need to be within the map coverage area. This places high demands on vehicle configuration and limits the scope of use.

[0009] (2) The camera needs to have strong image recognition capabilities, which in turn requires a large amount of image data from the junction port to train the algorithm, consuming a lot of manpower and resources.

[0010] (3) Autonomous vehicles need to be equipped with V2X devices and the vehicles need to be within the V2X coverage area. This places high demands on vehicle configuration and has a limited scope of use. Summary of the Invention

[0011] This application provides a method, apparatus, electronic device, and storage medium for predicting merging into a target ahead, in order to solve the problems in related technologies where vehicles need to use maps, cameras, or V2X devices to detect whether they are in a merging area when making merging into a target, which results in high vehicle configuration requirements, limited application range, and a large amount of manpower and resources being consumed.

[0012] The first aspect of this application provides a method for predicting a target vehicle merging into the lane ahead, comprising the following steps: obtaining the location information of a current vehicle and determining a target vehicle merging into the lane based on the location information of the current vehicle; obtaining multiple interacting vehicles in the same lane and adjacent lanes as the target vehicle merging into the lane, and calculating the sum of merging attitude coefficients of the multiple interacting vehicles when they are in a merging posture; and when the target vehicle merging into the lane and the sum of the merging attitude coefficients is greater than a preset value, calculating a predicted lateral position value of the target vehicle merging into the lane where the current vehicle is located, and predicting whether the target vehicle merging into the lane based on the predicted value.

[0013] Based on the aforementioned technical means, by identifying merging target vehicles, it can predict in advance whether merging vehicles will enter the lane, which helps the longitudinal planning part of the autonomous vehicle to plan deceleration and execute braking actions in advance, avoiding collisions with the vehicle in front to ensure driving safety, and avoiding emergency braking to improve driving comfort.

[0014] Furthermore, in one embodiment of this application, after determining the target merging vehicle based on the current vehicle's position information, the method further includes: determining whether the lateral velocity of the target merging vehicle relative to the centerline of the lane where the current vehicle is located is greater than a first preset velocity, and whether the heading angle of the target merging vehicle relative to the lane where the current vehicle is located on the side lane line of the target merging vehicle is greater than a first preset angle value; if the lateral velocity of the target merging vehicle relative to the centerline of the lane where the current vehicle is located is greater than the first preset velocity, and the heading angle of the target merging vehicle relative to the lane where the current vehicle is located on the side lane line of the target merging vehicle is greater than the first preset angle value, then it is determined that the target merging vehicle is in a merging posture.

[0015] Based on the aforementioned technical means, by determining whether the target vehicle is merging into the flow by setting preset speed and angle values, vehicle driving planning can be carried out in advance to avoid emergency braking.

[0016] Further, in one embodiment of this application, the plurality of interactive vehicles includes the interactive vehicle in front of the target cutting-in vehicle, the interactive vehicle behind it, and the interactive vehicle in the adjacent lane. The calculation of the sum of the merging attitude coefficients of the plurality of interactive vehicles when they are in a merging attitude includes: determining whether the interactive vehicle in front is in the merging attitude, and if so, the merging attitude coefficient of the interactive vehicle in front is a first preset value; otherwise, the merging attitude coefficient of the interactive vehicle in front is 0; determining whether the interactive vehicle behind is in the merging attitude, and if so, the merging attitude coefficient of the interactive vehicle behind is a second preset value; otherwise, the merging attitude coefficient of the interactive vehicle behind is 0; determining whether the interactive vehicle in the adjacent lane is in the merging attitude, and if so, the merging attitude coefficient of the interactive vehicle in the adjacent lane is a third preset value; otherwise, the merging attitude coefficient of the interactive vehicle in the adjacent lane is 0; and obtaining the sum of the merging attitude coefficients based on the sum of the first preset value, the second preset value, and the third preset value.

[0017] By using the aforementioned technical means and obtaining attitude coefficients, driving safety is improved.

[0018] Further, in one embodiment of this application, determining whether the preceding interactive vehicle is in the merging posture includes: determining whether the lateral velocity of the preceding interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than a second preset speed; whether the heading angle of the preceding interactive vehicle relative to the target vehicle's side lane line in the lane where the current vehicle is located is greater than a second preset angle value; whether the longitudinal speed of the preceding interactive vehicle is greater than a third preset speed; whether the distance between the preceding interactive vehicle and the target merging vehicle is less than a first preset distance; and whether the distance between the preceding interactive vehicle and the centerline of the lane where the current vehicle is located is less than the distance between the target merging vehicle and the centerline of the lane where the current vehicle is located. The distance to the lane centerline; if the lateral speed of the preceding interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than the second preset speed, and the heading angle of the preceding interactive vehicle relative to the lane where the current vehicle is located on the side lane line of the target merging vehicle is greater than the second preset angle value, and the longitudinal speed of the preceding interactive vehicle is greater than the third preset speed, and the distance between the preceding interactive vehicle and the target merging vehicle is less than the first preset distance, and the distance between the preceding interactive vehicle and the centerline of the lane where the current vehicle is located is less than the distance between the target merging vehicle and the centerline of the lane where the current vehicle is located, then it is determined that the preceding interactive vehicle is in the merging posture.

[0019] Based on the aforementioned technical means, the rationality and foresight of vehicle decision-making and planning are ensured by determining whether the vehicles ahead are in a merging posture.

[0020] Further, in one embodiment of this application, determining whether the following interactive vehicle is in the merging posture includes: determining whether the lateral velocity of the following interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than a fourth preset speed; whether the heading angle of the following interactive vehicle relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than a third preset angle value; whether the longitudinal speed of the following interactive vehicle is greater than a fifth preset speed; whether the distance between the following interactive vehicle and the target merging vehicle is less than a first preset distance; and whether the distance between the following interactive vehicle and the centerline of the lane where the current vehicle is located is greater than the distance between the target merging vehicle and the current vehicle. The distance from the centerline of the lane; if the lateral speed of the rear interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than the fourth preset speed, and the heading angle of the rear interactive vehicle relative to the target vehicle's side lane line in the lane where the current vehicle is located is greater than the third preset angle value, and the longitudinal speed of the rear interactive vehicle is greater than the fifth preset speed, and the distance between the rear interactive vehicle and the target cutting vehicle is less than the second preset distance, and the distance between the rear interactive vehicle and the centerline of the lane where the current vehicle is located is greater than the distance between the target cutting vehicle and the centerline of the lane where the current vehicle is located, then it is determined that the rear interactive vehicle is in the merging posture.

[0021] Based on the aforementioned technical means, the rationality and foresight of vehicle decision-making and planning are ensured by determining whether the vehicles behind are in a merging posture.

[0022] Further, in one embodiment of this application, determining whether the adjacent lane vehicles are in the merging posture includes: determining whether the lateral velocity of the adjacent lane vehicles relative to the centerline of the lane where the current vehicle is located is greater than a sixth preset velocity, whether the heading angle of the adjacent lane vehicles relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than a fourth preset angle value, whether the longitudinal speed of the adjacent lane vehicles is greater than a seventh preset velocity, and whether the distance of the adjacent lane vehicles from the target cutting-in vehicle is less than a third preset distance; if the lateral velocity of the adjacent lane vehicles relative to the centerline of the lane where the current vehicle is located is greater than the sixth preset velocity, and the heading angle of the adjacent lane vehicles relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than the fourth preset angle value, and the longitudinal speed of the adjacent lane vehicles is greater than the seventh preset velocity, and the distance of the adjacent lane vehicles from the target cutting-in vehicle is less than the third preset distance, then it is determined that the adjacent lane vehicles are in the merging posture.

[0023] Based on the aforementioned technical means, the rationality and foresight of vehicle decision-making and planning are ensured by determining whether vehicles in adjacent lanes are in a merging posture.

[0024] Further, in one embodiment of this application, calculating the predicted lateral position of the target cutting-in vehicle includes: calculating the predicted lateral position of the target cutting-in vehicle based on a preset prediction formula, wherein the preset prediction formula is:

[0025] L_Lat_Pred=L_Lat+V_Lat×T;

[0026] Where L_Lat_Pred is the predicted value of the target cutting vehicle's relative lateral position, L_Lat is the target cutting vehicle's relative lateral position, V_Lat is the target cutting vehicle's relative lateral velocity, and T is the prediction duration.

[0027] Based on the aforementioned technical means, the predicted lateral position of the target vehicle is calculated using a prediction formula, ensuring the accuracy of the merging target.

[0028] Furthermore, in one embodiment of this application, the step of predicting whether the target cutting vehicle will merge into the lane where the current vehicle is located based on the predicted value includes: if the predicted value is in the lane where the current vehicle is located, then it is determined that the target cutting vehicle will merge into the lane where the current vehicle is located; otherwise, it is determined that the target cutting vehicle will not merge into the lane where the current vehicle is located.

[0029] Based on the aforementioned technical means, the calculated prediction values ​​can be used to determine in advance whether a target vehicle will merge into the current lane, ensuring the rationality and foresight of vehicle decision-making and planning.

[0030] A second aspect of this application provides a device for predicting a target merging and cutting into a lane, comprising: an acquisition module for acquiring the position information of a current vehicle and determining a target merging vehicle based on the position information of the current vehicle; a calculation module for acquiring multiple interacting vehicles in the same lane and adjacent lanes as the target merging vehicle and calculating the sum of merging attitude coefficients of the multiple interacting vehicles when they are in a merging posture; and a prediction module for calculating a predicted lateral position value of the target merging vehicle when the target merging vehicle is in a merging posture and the sum of the merging attitude coefficients is greater than a preset value, and predicting whether the target merging vehicle will merge into the lane where the current vehicle is located based on the predicted value.

[0031] Furthermore, in one embodiment of this application, after determining the target merging vehicle based on the current vehicle's position information, the acquisition module further includes: a first judgment unit, configured to determine whether the lateral velocity of the target merging vehicle relative to the centerline of the lane where the current vehicle is located is greater than a first preset velocity, and whether the heading angle of the target merging vehicle relative to the lane where the current vehicle is located on the side lane line of the target merging vehicle is greater than a first preset angle value; and a determination unit, configured to determine that the target merging vehicle is in a merging posture if the lateral velocity of the target merging vehicle relative to the centerline of the lane where the current vehicle is located is greater than the first preset velocity, and the heading angle of the target merging vehicle relative to the lane where the current vehicle is located on the side lane line of the target merging vehicle is greater than the first preset angle value.

[0032] Further, in one embodiment of this application, the calculation module includes: a second judgment unit, configured to determine whether the preceding interactive vehicle is in the merging posture, and when the preceding interactive vehicle is in the merging posture, the merging posture coefficient of the preceding interactive vehicle is a first preset value; otherwise, the merging posture coefficient of the preceding interactive vehicle is 0; a third judgment unit, configured to determine whether the following interactive vehicle is in the merging posture, and when the following interactive vehicle is in the merging posture, the merging posture coefficient of the following interactive vehicle is a second preset value; otherwise, the merging posture coefficient of the following interactive vehicle is 0; a fourth judgment unit, configured to determine whether the adjacent lane interactive vehicle is in the merging posture, and when the adjacent lane interactive vehicle is in the merging posture, the merging posture coefficient of the adjacent lane interactive vehicle is a third preset value; otherwise, the merging posture coefficient of the adjacent lane interactive vehicle is 0; and a summing unit, configured to obtain the sum of the merging posture coefficients based on the sum of the first preset value, the second preset value, and the third preset value.

[0033] Further, in one embodiment of this application, the second determining unit is specifically used to: determine whether the lateral velocity of the preceding interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than a second preset speed; whether the heading angle of the preceding interactive vehicle relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than a second preset angle value; whether the longitudinal speed of the preceding interactive vehicle is greater than a third preset speed; whether the distance between the preceding interactive vehicle and the target cutting-in vehicle is less than a first preset distance; and whether the distance between the preceding interactive vehicle and the centerline of the lane where the current vehicle is located is less than the distance between the target cutting-in vehicle and the centerline of the lane where the current vehicle is located. Distance; if the lateral speed of the preceding interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than the second preset speed, and the heading angle of the preceding interactive vehicle relative to the lane where the current vehicle is located on the side lane line of the target merging vehicle is greater than the second preset angle value, and the longitudinal speed of the preceding interactive vehicle is greater than the third preset speed, and the distance between the preceding interactive vehicle and the target merging vehicle is less than the first preset distance, and the distance between the preceding interactive vehicle and the centerline of the lane where the current vehicle is located is less than the distance between the target merging vehicle and the centerline of the lane where the current vehicle is located, then it is determined that the preceding interactive vehicle is in the merging posture.

[0034] Furthermore, in one embodiment of this application, the third determining unit is specifically used to: determine whether the lateral velocity of the rear interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than a fourth preset speed; whether the heading angle of the rear interactive vehicle relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than a third preset angle value; whether the longitudinal speed of the rear interactive vehicle is greater than a fifth preset speed; whether the distance between the rear interactive vehicle and the target cutting-in vehicle is less than a second preset distance; and whether the distance between the rear interactive vehicle and the centerline of the lane where the current vehicle is located is greater than the distance between the target cutting-in vehicle and the centerline of the lane where the current vehicle is located. The distance; if the lateral speed of the rear interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than the fourth preset speed, and the heading angle of the rear interactive vehicle relative to the target vehicle's side lane line in the lane where the current vehicle is located is greater than the third preset angle value, and the longitudinal speed of the rear interactive vehicle is greater than the fifth preset speed, and the distance between the rear interactive vehicle and the target cutting-in vehicle is less than the second preset distance, and the distance between the rear interactive vehicle and the centerline of the lane where the current vehicle is located is greater than the distance between the target cutting-in vehicle and the centerline of the lane where the current vehicle is located, then it is determined that the rear interactive vehicle is in the merging posture.

[0035] Further, in one embodiment of this application, the fourth determining unit is specifically used to: determine whether the lateral velocity of the adjacent lane interaction vehicle relative to the centerline of the lane where the current vehicle is located is greater than a sixth preset velocity, whether the heading angle of the adjacent lane interaction vehicle relative to the lane line of the target vehicle side of the lane where the current vehicle is located is greater than a fourth preset angle value, whether the longitudinal speed of the adjacent lane interaction vehicle is greater than a seventh preset velocity, and whether the distance of the adjacent lane interaction vehicle to the target cutting-in vehicle is less than a third preset distance; if the lateral velocity of the adjacent lane interaction vehicle relative to the centerline of the lane where the current vehicle is located is greater than the sixth preset velocity, and the heading angle of the adjacent lane interaction vehicle relative to the lane line of the target vehicle side of the lane where the current vehicle is located is greater than the fourth preset angle value, and the longitudinal speed of the adjacent lane interaction vehicle is greater than the seventh preset velocity, and the distance of the adjacent lane interaction vehicle to the target cutting-in vehicle is less than the third preset distance, then it is determined that the adjacent lane interaction vehicle is in the merging posture.

[0036] Furthermore, in one embodiment of this application, the prediction module includes: a calculation unit, configured to calculate a predicted lateral position of the target cutting-in vehicle based on a preset prediction formula, wherein the preset prediction formula is:

[0037] L_Lat_Pred=L_Lat+V_Lat×T;

[0038] Where L_Lat_Pred is the predicted value of the target cutting vehicle's relative lateral position, L_Lat is the target cutting vehicle's relative lateral position, V_Lat is the target cutting vehicle's relative lateral velocity, and T is the prediction duration.

[0039] Furthermore, in one embodiment of this application, the prediction module includes: a fifth judgment unit, configured to determine that if the predicted value is in the lane where the current vehicle is located, the target merging vehicle will merge into the lane where the current vehicle is located; otherwise, the target merging vehicle will not merge into the lane where the current vehicle is located.

[0040] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the forward target bus stop prediction method as described in the above embodiments.

[0041] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the forward target confluence cut-in prediction method as described in the above embodiments.

[0042] This application embodiment determines multiple interacting vehicles in the same and adjacent lanes as the target vehicle by acquiring the current vehicle's location information, and calculates the sum of merging attitude coefficients when the multiple interacting vehicles are in a merging posture. When the target vehicle is in a merging posture and the sum of the merging attitude coefficients is greater than a preset value, its lateral position prediction value is calculated, and based on the prediction value, it is predicted whether the target vehicle will merge into the lane currently occupied by the vehicle. This solves the problems of vehicles needing to use maps, cameras, or V2X devices to detect whether they are in a merging area when making a target merging cut-in, resulting in high vehicle configuration requirements, limited usage range, and significant manpower and material resources.

[0043] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0044] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0045] Figure 1 This is a flowchart of a method for predicting the entry of a target confluence according to an embodiment of this application;

[0046] Figure 2 This is a schematic diagram of a forward merging target according to an embodiment of this application;

[0047] Figure 3 This is a schematic diagram illustrating the division of a target interest region according to an embodiment of this application;

[0048] Figure 4 This is a schematic diagram of interactive vehicles around a target of interest according to an embodiment of this application;

[0049] Figure 5 This is a block diagram of a forward target confluence cut-in prediction device according to an embodiment of this application;

[0050] Figure 6 This is a schematic diagram of an electronic device according to an embodiment of this application.

[0051] Explanation of reference numerals in the attached diagram: 10 - Forward target confluence cut-in prediction device; 100 - Acquisition module; 200 - Calculation module; 300 - Prediction module. Detailed Implementation

[0052] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0053] The following description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, and storage medium for predicting forward target merging and cutting into a lane according to embodiments of this application. Addressing the issue mentioned in the background art where vehicles need to use maps, cameras, or V2X devices to detect whether they are in a merging area when making a target merging and cutting in, resulting in high vehicle configuration requirements, limited usage range, and significant manpower and resource consumption, this application provides a method for predicting forward target merging and cutting into a lane. In this method, the location information of the current vehicle is obtained to determine multiple interacting vehicles in the same lane and adjacent lanes as the target vehicle, and the sum of merging attitude coefficients of the multiple interacting vehicles when they are in a merging posture is calculated. When the target vehicle is in a merging posture and the sum of the merging attitude coefficients is greater than a preset value, its lateral position prediction value is calculated, and based on the prediction value, it is predicted whether the target vehicle will merge into the lane currently occupied by the vehicle. This solves the problem that when vehicles merge into a target area, they need to use maps, cameras, or V2X devices to detect whether they are in the merging area, which results in high vehicle configuration requirements, limited application range, and a lot of manpower and resources. By identifying the target vehicle merging ahead and making advance predictions, it helps the vehicle to plan its deceleration and perform braking actions in advance, thereby avoiding collisions with the vehicle in front and improving safety and driving comfort.

[0054] Specifically, Figure 1 This is a flowchart illustrating a method for predicting the entry of a target confluence in an embodiment of this application.

[0055] like Figure 1 As shown, the method for predicting the convergence of a target ahead includes the following steps:

[0056] In step S101, the current vehicle's location information is obtained, and the target vehicle is determined based on the current vehicle's location information.

[0057] Specifically, such as Figure 2 As shown in the embodiments of this application, in order to ensure the rationality and foresight of vehicle decision-making and planning, it is first necessary to obtain the current vehicle's location information, filter target vehicles of interest based on its location information (i.e., target merging vehicles), and identify and predict the forward merging targets of the current vehicle, thereby avoiding collisions with the vehicle in front and improving driving safety and comfort.

[0058] The current vehicle's location information can be within the leftmost / rightmost two lanes of the road. The judgment conditions are: (1) the lateral distance between the road edge identified by the vehicle's front-view camera and the current vehicle is less than 6m, and the maximum detectable distance of the road edge is greater than 10m; (2) the lane line type of the left / right lane of the current vehicle is a wide dashed line. If either of the above two conditions is met, the current vehicle is considered to be within the range where merging may occur.

[0059] Furthermore, in one embodiment of this application, after determining the target merging vehicle based on the current vehicle's position information, the method further includes: determining whether the lateral velocity of the target merging vehicle relative to the centerline of the lane where the current vehicle is located is greater than a first preset velocity, and whether the heading angle of the target merging vehicle relative to the lane where the current vehicle is located on the side lane line is greater than a first preset angle value; if the lateral velocity of the target merging vehicle relative to the centerline of the lane where the current vehicle is located is greater than the first preset velocity, and the heading angle of the target merging vehicle relative to the lane where the current vehicle is located on the side lane line is greater than the first preset angle value, then it is determined that the target merging vehicle is in a merging posture.

[0060] The first preset speed and the first preset angle value can be thresholds set by relevant technicians or users according to actual needs, or thresholds obtained through multiple computer simulations, and are not specifically limited here.

[0061] Furthermore, in this embodiment of the application, after determining the target vehicle to cut in based on the current vehicle's location information, it is necessary to further filter out the forward target vehicles to cut in that require merging and cutting-in prediction, such as... Figure 3 As shown, the target vehicles RT3, RT4, RT5, and RT6, which are closest to the current vehicle in the longitudinal distance of the adjacent lane, can be selected as target vehicles for merging and merging prediction.

[0062] Furthermore, in this embodiment of the application, the selected target vehicles are analyzed to predict their attitudes. If a predicted target vehicle meets the following conditions, it is considered to be in a merging attitude:

[0063] (1) The lateral velocity of the target vehicle relative to the centerline of the lane where the current vehicle is located is greater than 0.5 m / s;

[0064] (2) The heading angle objHeading_Rel of the target cutting vehicle relative to the lane where the current vehicle is located, which is located on the side lane line of the target cutting vehicle, is greater than a certain threshold. This threshold is obtained from Table 1 based on the target longitudinal speed V_Long:

[0065] Table 1

[0066]

[0067] (3) The target longitudinal speed V_Long is greater than 20km / h.

[0068] By determining that the lateral velocity of the target vehicle relative to the centerline of the lane where the current vehicle is located and the heading angle relative to the lane where the target vehicle is located meet the above-mentioned conditions, it is determined that the target vehicle is in a merging attitude.

[0069] In step S102, multiple interacting vehicles in the same lane and adjacent lanes as the target vehicle are acquired, and the merging attitude coefficients of the multiple interacting vehicles when they are in the merging attitude are calculated.

[0070] Further, in one embodiment of this application, the multiple interactive vehicles include the interactive vehicle in front of the target vehicle, the interactive vehicle behind the target vehicle, and the interactive vehicle in the adjacent lane. Calculating the sum of the merging attitude coefficients of the multiple interactive vehicles when they are in a merging attitude includes: determining whether the interactive vehicle in front is in a merging attitude, and if so, the merging attitude coefficient of the interactive vehicle in front is a first preset value; otherwise, the merging attitude coefficient of the interactive vehicle in front is 0; determining whether the interactive vehicle behind is in a merging attitude, and if so, the merging attitude coefficient of the interactive vehicle behind is a second preset value; otherwise, the merging attitude coefficient of the interactive vehicle behind is 0; determining whether the interactive vehicle in the adjacent lane is in a merging attitude, and if so, the merging attitude coefficient of the interactive vehicle in the adjacent lane is a third preset value; otherwise, the merging attitude coefficient of the interactive vehicle in the adjacent lane is 0; and obtaining the sum of the merging attitude coefficients based on the sum of the first preset value, the second preset value, and the third preset value.

[0071] The first, second, and third preset values ​​can be thresholds set by relevant technical personnel or users according to actual needs, or thresholds obtained through multiple computer simulations; no specific limitations are made here.

[0072] Specifically, based on the target attitude analysis results of the target vehicle cutting in and its multiple interacting vehicles in the same and adjacent lanes, the target vehicle cutting in is determined to be a merging target if it meets the following two conditions: (1) the target vehicle cutting in is in a merging attitude; (2) the target vehicle cutting in and its multiple interacting vehicles in the same and adjacent lanes are in a merging attitude. The judgment method is as follows: when the front interacting vehicle and the rear cutting vehicle in the same lane of the target vehicle cutting in are in a merging attitude, the attitude coefficient is set to 1; otherwise, if the front interacting vehicle and the rear cutting vehicle in the same lane of the target vehicle cutting in do not exist or are not in a merging attitude, the attitude coefficient is set to 0; if the interacting vehicles in the adjacent lanes on both sides of the target vehicle cutting in are in a merging attitude, the attitude coefficient is set to 0.5; otherwise, if the interacting vehicles in the adjacent lanes on both sides do not exist or are not in a merging attitude, the attitude coefficient is set to 0. The coefficients obtained above are summed to obtain the merging attitude coefficient sum when multiple interacting vehicles are in a merging attitude.

[0073] Specifically, the application embodiment further filters the surrounding interacting vehicles of the selected target cutting-in vehicle, including multiple interacting vehicles in the same lane and adjacent lanes of the target cutting-in vehicle. These multiple interacting vehicles include interacting vehicles in front of the target cutting-in vehicle, vehicles cutting in behind it, and interacting vehicles in adjacent lanes. Figure 4 As shown, this application takes RT4 as an example, and then filters out the vehicle in front of the target vehicle RT6 in the same lane, the vehicle behind the target vehicle RT8 in the same lane, and RT1 and RT4 in adjacent lanes, and further analyzes the vehicle attitude of multiple interacting vehicles respectively.

[0074] Further, in one embodiment of this application, determining whether the preceding interactive vehicle is in a merging posture includes: determining whether the lateral velocity of the preceding interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than a second preset velocity, whether the heading angle of the preceding interactive vehicle relative to the lane line of the target vehicle on the side of the lane where the current vehicle is located is greater than a second preset angle value, whether the longitudinal velocity of the preceding interactive vehicle is greater than a third preset velocity, whether the distance between the preceding interactive vehicle and the target merging vehicle is less than a first preset distance, and whether the distance between the preceding interactive vehicle and the centerline of the lane where the current vehicle is located is less than the distance between the target merging vehicle and the centerline of the lane where the current vehicle is located; if the lateral velocity of the preceding interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than the second preset velocity, and the heading angle of the preceding interactive vehicle relative to the lane line of the target merging vehicle on the side of the lane where the current vehicle is located is greater than the second preset angle value, and the longitudinal velocity of the preceding interactive vehicle is greater than the third preset velocity, and the distance between the preceding interactive vehicle and the target merging vehicle is less than the first preset distance, and the distance between the preceding interactive vehicle and the centerline of the lane where the current vehicle is located is less than the distance between the target merging vehicle and the centerline of the lane where the current vehicle is located, then it is determined that the preceding interactive vehicle is in a merging posture.

[0075] The second preset speed and the second preset angle value can be a threshold set by relevant technicians or users according to actual needs, or a threshold obtained through multiple computer simulations, and no specific limitation is made here.

[0076] Specifically, if the vehicle in front of the current vehicle meets the following conditions in this application embodiment, it is considered to be in a merging posture: (1) the lateral velocity obj_V_Lat_Rel of the vehicle in front relative to the center line of the lane where the current vehicle is located is greater than 0.3 m / s; (2) the heading angle objHeading_Rel of the vehicle in front relative to the lane where the current vehicle is located on the side lane line of the target cutting vehicle is greater than a certain threshold, which is obtained by referring to Table 1 based on the target longitudinal speed V_Long; (3) the target longitudinal speed V_Long is greater than 20 km / h; (4) the longitudinal distance between the vehicle in front and the predicted target is less than 40 m; (5) the distance objDist2Ref_FrontCar of the vehicle in front from the center line of the lane where the current vehicle is located is less than the objDist2Ref_RT of the predicted target. If the vehicle in front meets the above conditions, it is considered to be in a merging posture.

[0077] Furthermore, in one embodiment of this application, determining whether a following vehicle is in a merging posture includes: determining whether the lateral velocity of the following vehicle relative to the centerline of the lane where the current vehicle is located is greater than a fourth preset velocity; whether the heading angle of the following vehicle relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than a third preset angle value; whether the longitudinal speed of the following vehicle is greater than a fifth preset velocity; whether the distance between the following vehicle and the target merging vehicle is less than a second preset distance; and whether the distance between the following vehicle and the centerline of the lane where the current vehicle is located is greater than the distance between the following vehicle and the target merging vehicle. The distance from the centerline of the lane where the preceding vehicle is located; if the lateral speed of the following vehicle relative to the centerline of the lane where the current vehicle is located is greater than the fourth preset speed, and the heading angle of the following vehicle relative to the target vehicle's side lane line in the lane where the current vehicle is located is greater than the third preset angle value, and the longitudinal speed of the following vehicle is greater than the fifth preset speed, and the distance between the following vehicle and the target cutting vehicle is less than the second preset distance, and the distance between the following vehicle and the centerline of the lane where the current vehicle is located is greater than the distance between the target cutting vehicle and the centerline of the lane where the current vehicle is located, then it is determined that the following vehicle is in a merging posture.

[0078] Specifically, if the following conditions are met by the rear interactive vehicle in this application embodiment, the rear interactive vehicle is considered to be in a merging posture: (1) the lateral velocity obj_V_Lat_Rel of the rear interactive vehicle relative to the center line of the lane where the current vehicle is located is greater than 0.6 m / s; (2) the heading angle objHeading_Rel of the front interactive vehicle relative to the lane where the current vehicle is located on the side lane line of the target cutting vehicle is greater than a certain threshold, which is obtained by referring to Table 1 based on the target longitudinal speed V_Long; (3) the target longitudinal speed V_Long is greater than 20 km / h; (4) the longitudinal distance between the front interactive vehicle and the predicted target is less than 40 m; (5) the distance objDist2Ref_RearCar of the front interactive vehicle from the center line of the lane where the current vehicle is located is greater than the predicted target's objDist2Ref_RT. If the front interactive vehicle meets the above conditions, the front interactive vehicle is considered to be in a merging posture.

[0079] Further, in one embodiment of this application, determining whether adjacent lane vehicles are in a merging posture includes: determining whether the lateral velocity of the adjacent lane vehicles relative to the centerline of the lane where the current vehicle is located is greater than a sixth preset velocity, whether the heading angle of the adjacent lane vehicles relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than a fourth preset angle value, whether the longitudinal speed of the adjacent lane vehicles is greater than a seventh preset velocity, and whether the distance of the adjacent lane vehicles from the target cutting-in vehicle is less than a third preset distance; if the lateral velocity of the adjacent lane vehicles relative to the centerline of the lane where the current vehicle is located is greater than the sixth preset velocity, and the heading angle of the adjacent lane vehicles relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than the fourth preset angle value, and the longitudinal speed of the adjacent lane vehicles is greater than the seventh preset velocity, and the distance of the adjacent lane vehicles from the target cutting-in vehicle is less than the third preset distance, then it is determined that the adjacent lane vehicles are in a merging posture.

[0080] Specifically, if the adjacent lane interaction vehicles in this application embodiment meet the following conditions, the preceding adjacent lane interaction vehicles are considered to be in a merging posture: (1) the lateral velocity obj_V_Lat_Rel of the adjacent lane interaction vehicle relative to the center line of the lane where the current vehicle is located is greater than 0.5m / s; (2) the heading angle objHeading_Rel of the adjacent lane interaction vehicle relative to the lane where the current vehicle is located on the side lane line of the target cutting vehicle is greater than a certain threshold, which is obtained by referring to Table 1 based on the target longitudinal speed V_Long; (3) the target longitudinal speed V_Long is greater than 20km / h; (4) the longitudinal distance between the preceding interaction vehicle and the predicted target is less than 20m. If the preceding interaction vehicle meets the above conditions, the preceding interaction vehicle is considered to be in a merging posture.

[0081] In step S103, when the target vehicle is in a merging attitude and the sum of the merging attitude coefficients is greater than a preset value, the lateral position prediction value of the target vehicle is calculated, and the target vehicle is predicted to merge into the lane where the current vehicle is located based on the prediction value.

[0082] Specifically, in this embodiment of the application, when the target cutting-in vehicle is in a merging attitude and the sum of the merging attitude coefficients is greater than 1, the predicted lateral position of the target cutting-in vehicle is calculated, wherein the preset prediction formula is:

[0083] L_Lat_Pred=L_Lat+V_Lat×T;

[0084] Where L_Lat_Pred is the predicted value of the relative lateral position of the target cutting vehicle, L_Lat is the relative lateral position of the target cutting vehicle, V_Lat is the relative lateral speed of the target cutting vehicle, and T is the prediction duration. Based on the analysis of the current lane status of the vehicle, if the current vehicle is in the range where merging may occur, then T is set to 3s; if the current vehicle is not in the range where merging may occur, then T is set to 1.5s.

[0085] Furthermore, in one embodiment of this application, predicting whether a target vehicle will merge into the lane currently occupied by the vehicle based on the predicted value includes: if the predicted value is in the lane currently occupied by the vehicle, then it is determined that the target vehicle will merge into the lane currently occupied by the vehicle; otherwise, it is determined that the target vehicle will not merge into the lane currently occupied by the vehicle.

[0086] Specifically, based on the above calculation of the predicted lateral position of the target cutting vehicle, if the predicted lateral position L_Lat_Pred of the target cutting vehicle is within the lane of the current vehicle, the prediction result is that the target cutting vehicle will enter the lane of the current vehicle; otherwise, the prediction result is that the target cutting vehicle will not enter the lane of the current vehicle.

[0087] In summary, based on the analysis of the forward target confluence cut-in prediction method in the embodiments of this application, it has the following advantages:

[0088] (1) By using the actual physical motion of multiple targets as the basis for judgment, this method can effectively reduce the error rate caused by insufficient detection accuracy of obstructed converging targets and has high accuracy.

[0089] (2) Only basic information such as single-target physical motion, multi-target behavior around the target vehicle, and lane line detection by the forward-looking camera are required for autonomous vehicles. No additional configuration or software algorithm development is needed, saving manpower and resources.

[0090] According to the forward target merging and cutting-in prediction method of this application embodiment, multiple interacting vehicles in the same lane and adjacent lanes of the target merging vehicle are determined by obtaining the current vehicle's position information. The merging attitude coefficients of the multiple interacting vehicles when they are in a merging posture are calculated. When the target merging vehicle is in a merging posture and the sum of the merging attitude coefficients is greater than a preset value, its lateral position prediction value is calculated, and the prediction value is used to predict whether the target merging vehicle will merge into the lane where the current vehicle is located. This solves the problems that when a vehicle is merging and cutting into a target lane, it needs to use maps, cameras, or V2X devices to detect whether the vehicle is in a merging area, which results in high vehicle configuration requirements, limited scope of use, and a large amount of manpower and resources. By identifying the forward merging target vehicle and making an early prediction, the method helps the vehicle to plan its deceleration and perform braking actions in advance, thereby avoiding collisions with the vehicle in front and improving safety and driving comfort.

[0091] Next, referring to the accompanying drawings, a forward target confluence cut-in prediction device according to an embodiment of this application is described.

[0092] Figure 5 This is a block diagram of the forward target confluence cut-in prediction device according to an embodiment of this application.

[0093] like Figure 5 As shown, the forward target confluence cut-in prediction device 10 includes: an acquisition module 100, a calculation module 200, and a prediction module 300.

[0094] The acquisition module 100 is used to acquire the current vehicle's location information and determine the target vehicle to cut in based on the current vehicle's location information.

[0095] The calculation module 200 is used to acquire multiple interacting vehicles in the same lane and adjacent lanes as the target vehicle, and to calculate the sum of the merging attitude coefficients of the multiple interacting vehicles when they are in a merging attitude; and

[0096] The prediction module 300 is used to calculate the predicted lateral position of the target vehicle when it is in a merging posture and the sum of the merging posture coefficients is greater than a preset value, and to predict whether the target vehicle will merge into the lane where the current vehicle is located based on the predicted value.

[0097] Furthermore, in one embodiment of this application, after determining the target vehicle based on the current vehicle's location information, the acquisition module 100 further includes: a first judgment unit and a determination unit.

[0098] The first judgment unit is used to determine whether the lateral speed of the target cutting vehicle relative to the center line of the lane where the current vehicle is located is greater than a first preset speed, and whether the heading angle of the target cutting vehicle relative to the lane where the current vehicle is located on the side lane line of the target cutting vehicle is greater than a first preset angle value.

[0099] The determining unit is configured to determine that the target vehicle is in a merging attitude if the lateral velocity of the target vehicle relative to the centerline of the lane where the current vehicle is located is greater than a first preset velocity, and the heading angle of the target vehicle relative to the lane where the current vehicle is located on the side lane line of the target vehicle is greater than a first preset angle value.

[0100] Furthermore, in one embodiment of this application, the calculation module 200 includes: a second judgment unit, a third judgment unit, a fourth judgment unit, and a summing unit.

[0101] The second judgment unit is used to determine whether the front interactive vehicle is in a merging posture. When the front interactive vehicle is in a merging posture, the merging posture coefficient of the front interactive vehicle is a first preset value; otherwise, the merging posture coefficient of the front interactive vehicle is 0.

[0102] The third judgment unit is used to determine whether the rear interactive vehicle is in a merging posture. When the rear interactive vehicle is in a merging posture, the merging posture coefficient of the rear interactive vehicle is the second preset value; otherwise, the merging posture coefficient of the rear interactive vehicle is 0.

[0103] The fourth judgment unit is used to determine whether the vehicles interacting in adjacent lanes are in a merging posture. When the vehicles interacting in adjacent lanes are in a merging posture, the merging posture coefficient of the vehicles interacting in adjacent lanes is the third preset value; otherwise, the merging posture coefficient of the vehicles interacting in adjacent lanes is 0.

[0104] The summation unit is used to obtain the sum of the convergence attitude coefficients based on the sum of the first preset value, the second preset value, and the third preset value.

[0105] Furthermore, in one embodiment of this application, the second determining unit is specifically used for:

[0106] The system determines whether the lateral speed of the vehicle ahead relative to the centerline of the lane where the current vehicle is located is greater than a second preset speed, whether the heading angle of the vehicle ahead relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than a second preset angle, whether the longitudinal speed of the vehicle ahead is greater than a third preset speed, whether the distance between the vehicle ahead and the target vehicle is less than a first preset distance, and whether the distance between the vehicle ahead and the centerline of the lane where the current vehicle is located is less than the distance between the target vehicle and the centerline of the lane where the current vehicle is located.

[0107] If the lateral velocity of the vehicle ahead relative to the centerline of the lane where the current vehicle is located is greater than the second preset velocity, and the heading angle of the vehicle ahead relative to the lane where the current vehicle is located on the side lane line of the target merging vehicle is greater than the second preset angle value, and the longitudinal speed of the vehicle ahead is greater than the third preset velocity, and the distance between the vehicle ahead and the target merging vehicle is less than the first preset distance, and the distance between the vehicle ahead and the centerline of the lane where the current vehicle is located is less than the distance between the target merging vehicle and the centerline of the lane where the current vehicle is located, then the vehicle ahead is determined to be in a merging posture.

[0108] Furthermore, in one embodiment of this application, the third determining unit is specifically used for:

[0109] The system determines whether the lateral speed of the vehicle behind is greater than the fourth preset speed relative to the centerline of the lane where the current vehicle is located, whether the heading angle of the vehicle behind is greater than the third preset angle value relative to the lane line of the target vehicle in the lane where the current vehicle is located, whether the longitudinal speed of the vehicle behind is greater than the fifth preset speed, whether the distance between the vehicle behind and the target vehicle is less than the second preset distance, and whether the distance between the vehicle behind and the centerline of the lane where the current vehicle is located is greater than the distance between the target vehicle and the centerline of the lane where the current vehicle is located.

[0110] If the lateral speed of the following vehicle relative to the centerline of the lane where the current vehicle is located is greater than the fourth preset speed, and the heading angle of the following vehicle relative to the target vehicle's side lane line in the lane where the current vehicle is located is greater than the third preset angle, and the longitudinal speed of the following vehicle is greater than the fifth preset speed, and the distance between the following vehicle and the target cutting vehicle is less than the second preset distance, and the distance between the following vehicle and the centerline of the lane where the current vehicle is located is greater than the distance between the target cutting vehicle and the centerline of the lane where the current vehicle is located, then the following vehicle is determined to be in a merging posture.

[0111] Furthermore, in one embodiment of this application, the fourth determination unit is specifically used for:

[0112] Determine whether the lateral speed of the vehicle interacting with the adjacent lane relative to the centerline of the lane where the current vehicle is located is greater than the sixth preset speed, whether the heading angle of the vehicle interacting with the adjacent lane relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than the fourth preset angle value, whether the longitudinal speed of the vehicle interacting with the adjacent lane is greater than the seventh preset speed, and whether the distance of the vehicle interacting with the adjacent lane to the target cutting vehicle is less than the third preset distance.

[0113] If the lateral speed of the adjacent lane interaction vehicle relative to the centerline of the lane where the current vehicle is located is greater than the sixth preset speed, and the heading angle of the adjacent lane interaction vehicle relative to the target vehicle's side lane line in the lane where the current vehicle is located is greater than the fourth preset angle value, and the longitudinal speed of the adjacent lane interaction vehicle is greater than the seventh preset speed, and the distance of the adjacent lane interaction vehicle to the target cutting vehicle is less than the third preset distance, then the adjacent lane interaction vehicles are determined to be in a merging posture.

[0114] Furthermore, in one embodiment of this application, the prediction module 300 includes:

[0115] The calculation unit is used to calculate the predicted lateral position of the target cutting vehicle based on a preset prediction formula, wherein the preset prediction formula is:

[0116] L_Lat_Pred=L_Lat+V_Lat×T;

[0117] Where L_Lat_Pred is the predicted value of the target cutting vehicle's relative lateral position, L_Lat is the target cutting vehicle's relative lateral position, V_Lat is the target cutting vehicle's relative lateral velocity, and T is the prediction duration.

[0118] Furthermore, in one embodiment of this application, the prediction module 300 includes:

[0119] The fifth judgment unit is used to determine that if the predicted value is in the lane where the current vehicle is located, the target vehicle will merge into the lane where the current vehicle is located; otherwise, the target vehicle will not merge into the lane where the current vehicle is located.

[0120] According to the forward target merging and cutting-in prediction device of this application embodiment, the device determines multiple interacting vehicles in the same lane and adjacent lanes as the target merging vehicle by acquiring the current vehicle's position information, and calculates the sum of merging attitude coefficients of the multiple interacting vehicles when they are in a merging posture. When the target merging vehicle is in a merging posture and the sum of the merging attitude coefficients is greater than a preset value, the device calculates its lateral position prediction value, and predicts whether the target merging vehicle will merge into the lane where the current vehicle is located based on the prediction value. This solves the problems of vehicles needing to use maps, cameras, or V2X devices to detect whether they are in a merging area when making a target merging and cutting-in, resulting in high vehicle configuration requirements, limited application range, and high manpower and material resources. By identifying the forward merging target vehicle and making an early prediction, the device helps the vehicle to plan its deceleration and perform braking actions in advance, thereby avoiding collisions with the vehicle in front and improving safety and driving comfort.

[0121] Figure 6 This application provides a schematic diagram of the structure of an electronic device. The electronic device may include:

[0122] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0123] When the processor 602 executes the program, it implements the forward target confluence cut-in prediction method provided in the above embodiments.

[0124] Furthermore, electronic devices also include:

[0125] Communication interface 603 is used for communication between memory 601 and processor 602.

[0126] The memory 601 is used to store computer programs that can run on the processor 602.

[0127] The memory 601 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0128] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0129] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0130] The processor 602 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of this application.

[0131] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described forward target confluence cut-in prediction method.

[0132] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0133] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0134] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0135] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0136] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0137] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for predicting the convergence and entry of a target ahead, characterized in that, Includes the following steps: Obtain the current vehicle's location information, and determine the target vehicle to cut in based on the current vehicle's location information; Acquire multiple interacting vehicles in the same lane and adjacent lanes as the target vehicle, and calculate the merging attitude coefficients of the multiple interacting vehicles when they are in a merging attitude. as well as When the target merging vehicle is in a merging posture and the sum of the merging posture coefficients is greater than a preset value, the lateral position prediction value of the target merging vehicle is calculated, and the target merging vehicle is predicted to merge into the lane where the current vehicle is located based on the prediction value.

2. The method according to claim 1, characterized in that, After determining the target vehicle to cut in based on the current vehicle's location information, the process further includes: Determine whether the lateral velocity of the target cutting vehicle relative to the centerline of the lane where the current vehicle is located is greater than a first preset velocity, and whether the heading angle of the target cutting vehicle relative to the lane where the current vehicle is located on the side lane line of the target cutting vehicle is greater than a first preset angle value; If the lateral velocity of the target vehicle relative to the centerline of the lane where the current vehicle is located is greater than the first preset velocity, and the heading angle of the target vehicle relative to the lane where the current vehicle is located on the side lane line of the target vehicle is greater than the first preset angle value, then the target vehicle is determined to be in a merging posture.

3. The method according to claim 2, characterized in that, The plurality of interacting vehicles includes the interacting vehicles in front of the target cutting-in vehicle, the interacting vehicles behind the target cutting-in vehicle, and the interacting vehicles in adjacent lanes. The calculation of the sum of the merging attitude coefficients of the plurality of interacting vehicles when they are in a merging attitude includes: Determine whether the preceding interactive vehicle is in the merging posture, and when the preceding interactive vehicle is in the merging posture, the merging posture coefficient of the preceding interactive vehicle is a first preset value; otherwise, the merging posture coefficient of the preceding interactive vehicle is 0. Determine whether the rear interactive vehicle is in the merging posture, and when the rear interactive vehicle is in the merging posture, the merging posture coefficient of the rear interactive vehicle is a second preset value; otherwise, the merging posture coefficient of the rear interactive vehicle is 0. Determine whether the vehicles interacting in adjacent lanes are in the merging posture. If the vehicles interacting in adjacent lanes are in the merging posture, the merging posture coefficient of the vehicles interacting in adjacent lanes is a third preset value; otherwise, the merging posture coefficient of the vehicles interacting in adjacent lanes is 0. The convergence attitude coefficient is obtained by summing the first preset value, the second preset value, and the third preset value.

4. The method according to claim 3, characterized in that, The step of determining whether the preceding interactive vehicle is in the merging posture includes: The system determines whether the lateral speed of the vehicle ahead relative to the centerline of the lane where the current vehicle is located is greater than a second preset speed, whether the heading angle of the vehicle ahead relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than a second preset angle, whether the longitudinal speed of the vehicle ahead is greater than a third preset speed, whether the distance between the vehicle ahead and the target cutting vehicle is less than a first preset distance, and whether the distance between the vehicle ahead and the centerline of the lane where the current vehicle is located is less than the distance between the target cutting vehicle and the centerline of the lane where the current vehicle is located. If the lateral velocity of the preceding interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than the second preset velocity, and the heading angle of the preceding interactive vehicle relative to the lane where the current vehicle is located on the side lane of the target merging vehicle is greater than the second preset angle value, and the longitudinal speed of the preceding interactive vehicle is greater than the third preset velocity, and the distance between the preceding interactive vehicle and the target merging vehicle is less than the first preset distance, and the distance between the preceding interactive vehicle and the centerline of the lane where the current vehicle is located is less than the distance between the target merging vehicle and the centerline of the lane where the current vehicle is located, then it is determined that the preceding interactive vehicle is in the merging posture.

5. The method according to claim 3, characterized in that, The step of determining whether the following interactive vehicle is in the merging posture includes: The system determines whether the lateral speed of the rear interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than a fourth preset speed, whether the heading angle of the rear interactive vehicle relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than a third preset angle, whether the longitudinal speed of the rear interactive vehicle is greater than a fifth preset speed, whether the distance between the rear interactive vehicle and the target cutting vehicle is less than a second preset distance, and whether the distance between the rear interactive vehicle and the centerline of the lane where the current vehicle is located is greater than the distance between the target cutting vehicle and the centerline of the lane where the current vehicle is located. If the lateral velocity of the rear interactive vehicle relative to the centerline of the lane where the current vehicle is located is greater than the fourth preset velocity, and the heading angle of the rear interactive vehicle relative to the target vehicle's side lane line in the lane where the current vehicle is located is greater than the third preset angle value, and the longitudinal speed of the rear interactive vehicle is greater than the fifth preset velocity, and the distance between the rear interactive vehicle and the target cutting-in vehicle is less than the second preset distance, and the distance between the rear interactive vehicle and the centerline of the lane where the current vehicle is located is greater than the distance between the target cutting-in vehicle and the centerline of the lane where the current vehicle is located, then it is determined that the rear interactive vehicle is in the merging posture.

6. The method according to claim 3, characterized in that, The step of determining whether the vehicles interacting in adjacent lanes are in the merging posture includes: Determine whether the lateral speed of the adjacent lane interaction vehicle relative to the centerline of the lane where the current vehicle is located is greater than a sixth preset speed, whether the heading angle of the adjacent lane interaction vehicle relative to the lane line of the target vehicle in the lane where the current vehicle is located is greater than a fourth preset angle value, whether the longitudinal speed of the adjacent lane interaction vehicle is greater than a seventh preset speed, and whether the distance of the adjacent lane interaction vehicle to the target cutting vehicle is less than a third preset distance. If the lateral velocity of the adjacent lane interaction vehicle relative to the centerline of the lane where the current vehicle is located is greater than the sixth preset velocity, and the heading angle of the adjacent lane interaction vehicle relative to the target vehicle's side lane line in the lane where the current vehicle is located is greater than the fourth preset angle value, and the longitudinal speed of the adjacent lane interaction vehicle is greater than the seventh preset velocity, and the distance of the adjacent lane interaction vehicle to the target cutting vehicle is less than the third preset distance, then it is determined that the adjacent lane interaction vehicle is in the merging posture.

7. The method according to claim 1, characterized in that, The calculation of the predicted lateral position of the target cutting-in vehicle includes: Based on a preset prediction formula, the predicted lateral position of the target cutting vehicle is calculated, wherein the preset prediction formula is: L_Lat_Pred=L_Lat+V_Lat×T; Where L_Lat_Pred is the predicted value of the target cutting vehicle's relative lateral position, L_Lat is the target cutting vehicle's relative lateral position, V_Lat is the target cutting vehicle's relative lateral velocity, and T is the prediction duration.

8. The method according to claim 7, characterized in that, The step of predicting whether the target cutting vehicle will merge into the lane currently occupied by the vehicle based on the predicted value includes: If the predicted value is in the lane where the current vehicle is located, it is determined that the target vehicle will merge into the lane where the current vehicle is located; otherwise, it is determined that the target vehicle will not merge into the lane where the current vehicle is located.

9. A device for predicting the convergence and entry of a target ahead, characterized in that, include: The acquisition module is used to acquire the current vehicle's location information and determine the target vehicle to cut in based on the current vehicle's location information; The calculation module is used to acquire multiple interacting vehicles in the same lane and adjacent lanes as the target vehicle, and to calculate the merging attitude coefficients of the multiple interacting vehicles when they are in a merging attitude. as well as The prediction module is used to calculate the lateral position prediction value of the target merging vehicle when the target merging vehicle is in a merging posture and the sum of the merging posture coefficients is greater than a preset value, and to predict whether the target merging vehicle will merge into the lane where the current vehicle is located based on the prediction value.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the forward target confluence cut-in prediction method as described in any one of claims 1-8.

Images