Driving state prediction method and device, vehicle-mounted terminal, vehicle and storage medium

Abstract

The embodiment of the invention discloses a driving state prediction method and device, a vehicle-mounted terminal, a vehicle and a storage medium. The method comprises the steps of obtaining vehicle driving information and lane line information of a target vehicle; and determining a driving state of the target vehicle based on the lane line based on the vehicle driving information and the lane line information. Therefore, the driving state of the target vehicle can be determined only according to the vehicle driving information and the lane line information of the target vehicle, the relation between the vehicle and the environment information is established through the vehicle driving information and the lane line information of the target vehicle, and the relation between the target vehicle and the lane line in the actual driving scene is accurately obtained. Therefore, the driving state of the target vehicle is accurately determined on the basis of low calculation power demand, and the driving state prediction efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a driving state prediction method, device, vehicle-mounted terminal, vehicle and storage medium. Background Art

[0002] In intelligent driving scenarios, in order to ensure vehicle safety and more intelligent driving and avoid collisions with other vehicles, it is necessary to predict the vehicle's motion state. In existing driving state prediction methods, a state model is often established to predict the vehicle's driving state based on the vehicle's motion state information.

[0003] In the process of research and practice of existing technologies, it was found that the existing driving state prediction method has a complex modeling process for the state model, has high computing power requirements, and cannot stably and accurately predict the driving state of the vehicle in complex driving scenarios, which makes the driving state prediction efficiency low. Summary of the invention

[0004] The embodiments of the present application provide a driving state prediction method, device, vehicle-mounted terminal, vehicle and storage medium, which can accurately determine the driving state of a target vehicle in an actual driving scenario on the basis of low computational complexity, thereby improving the efficiency of driving state prediction.

[0005] In order to achieve the above object, according to a first aspect of the present application, a driving state prediction method is provided, the method comprising:

[0006] Obtain vehicle driving information and lane line information of the target vehicle;

[0007] Based on the vehicle driving information and the lane line information, a driving state of the target vehicle based on the lane line is determined.

[0008] In some embodiments, determining the driving state of the target vehicle based on the lane line based on the vehicle driving information and the lane line information includes: determining a reference lane line adjacent to the target vehicle on the lane based on the lane line information; determining the driving state of the target vehicle based on the lane line based on the reference lane line and the vehicle driving information.

[0009] In some embodiments, determining the driving state of the target vehicle based on the lane line based on the reference lane line and the vehicle driving information includes: determining a first target historical trajectory equation based on the reference lane line and the vehicle driving information; determining the driving state of the target vehicle based on the first target historical trajectory equation.

[0010] In some embodiments, determining the first target historical trajectory equation based on the reference lane line and the vehicle driving information includes: obtaining a first driving distance and a first lateral distance according to the lane line equation of the reference lane line and the vehicle driving information, the first driving distance being the distance traveled by the target vehicle between a first moment and a second moment, and the first lateral distance being the distance between the target vehicle and the reference lane line at the second moment; determining a trajectory curve of the historical trajectory of the target vehicle based on the first driving distance and the first lateral distance to obtain a first target historical trajectory equation.

[0011] In some embodiments, determining the trajectory curve of the historical trajectory of the target vehicle based on the first driving distance and the first lateral distance to obtain a first target historical trajectory equation includes: obtaining a first angle value, the first angle value indicating the angle between the driving direction of the target vehicle and the reference lane line at the second moment; if the absolute value of the first lateral distance is less than a first preset distance threshold and the absolute value of the first angle value is less than a first preset angle threshold, then determining the curve of the historical trajectory of the target vehicle based on the first driving distance and the first lateral distance to obtain a first target historical trajectory equation.

[0012] In some embodiments, if the absolute value of the first lateral distance is less than a first preset distance threshold and the absolute value of the first angle value is less than a first preset angle threshold, then based on the first driving distance and the first lateral distance, the curve of the historical trajectory of the target vehicle is determined to obtain a first target historical trajectory equation, including: obtaining a second lateral distance, the second lateral distance being a lane line equation passing through the reference lane line, and predicting the distance between the target vehicle and the reference lane line at a preset longitudinal distance in front of the target vehicle; if the absolute value of the first lateral distance is less than the first preset distance threshold and the absolute value of the first angle value is less than the first preset angle threshold, and the second lateral distance is not greater than the second preset distance threshold, based on the first driving distance and the first lateral distance, the quadratic curve of the historical trajectory of the target vehicle is determined to obtain a first target historical trajectory equation.

[0013] In some embodiments, the driving state includes a driving state of crossing a lane line, and determining the driving state of the target vehicle based on the lane line based on the reference lane line and the vehicle driving information includes: determining an adjacent reference lane line of the target vehicle in the reference lane line; and judging whether the target vehicle is in a driving state of crossing a lane line based on the adjacent reference lane line and the vehicle driving information.

[0014] In some embodiments, the driving state includes at least one of a driving state along a line, a lane change driving state, and a large curve driving state. The determining the driving state of the target vehicle based on the lane line based on the reference lane line and the vehicle driving information includes: determining the lane line state of the target vehicle based on the reference lane line, the lane line state including a standard lane state and a non-standard lane line state; determining whether the target vehicle belongs to at least one of a driving state along a line, a lane change driving state, and a large curve driving state based on the lane line state and the vehicle driving information.

[0015] In some embodiments, determining the lane line state of the target vehicle based on the reference lane line includes: if the target vehicle lacks the reference lane line on at least one side, determining that the lane line state of the target vehicle belongs to a non-standard lane state; if the target vehicle has reference lane lines on both sides and the lane width between the reference lane lines is within a preset lane width range, determining that the lane line state of the target vehicle belongs to a standard lane state; if the target vehicle has reference lane lines on both sides and the lane width between the reference lane lines is not within a preset lane width range, determining that the lane line state of the target vehicle belongs to a non-standard lane state.

[0016] In some embodiments, based on the lane line state and the vehicle driving information, it is determined whether the target vehicle is in a driving state along the line or a lane changing driving state, including: when the lane line state belongs to a non-standard lane state, based on the vehicle driving information and the lane line information of the reference lane line, it is determined whether the target vehicle is in a driving state along the line; when the lane line state belongs to a standard lane state, based on the vehicle driving information and the lane line information of the reference lane line, it is determined whether the target vehicle is in a lane changing driving state.

[0017] In some embodiments, the determining whether the target vehicle is in a driving along the line state based on the vehicle driving information and the lane line information of the reference lane line includes: based on the vehicle driving information, obtaining a curve of the historical trajectory of the target vehicle in the vehicle coordinate system of the target vehicle, and obtaining a second target historical trajectory equation; based on the second target historical trajectory equation and the lane line equation of the reference lane line, judging whether the target vehicle is in a driving along the line state along the current reference lane line.

[0018] In some embodiments, in the standard lane state, there are reference lane lines on both sides of the target vehicle, and determining whether the target vehicle is in a lane changing driving state based on the vehicle driving information and the lane line information of the reference lane lines includes: obtaining a second angle value based on the lane line equation of the reference lane line, and the second angle value indicates the angles between the reference lane lines on both sides of the target vehicle and the driving direction of the target vehicle; if the absolute values ​​of the second angle values ​​are less than the corresponding second preset angle thresholds, and the continuous duration of the target vehicle in the standard lane state exceeds the first preset duration, based on the vehicle driving information and the lane line information, obtaining a curve of the historical trajectory of the target vehicle, and obtaining a third target historical trajectory equation; based on the third target historical trajectory equation, determining whether the target vehicle is in a lane changing driving state.

[0019] In some embodiments, determining whether the target vehicle belongs to a lane changing driving state based on the third target historical trajectory equation includes: determining whether the target vehicle belongs to one of a plurality of lane changing driving sub-states included in the lane changing driving state based on the third target historical trajectory equation, the lane changing driving sub-states including: driving along a standard lane, changing lanes, pre-completing lane change, completing lane change, and failing lane change.

[0020] In some embodiments, the process of obtaining a curve of the historical trajectory of the target vehicle based on the vehicle driving information and the lane line information to obtain a third target historical trajectory equation includes: obtaining a second driving distance of the target vehicle within a preset update duration based on the vehicle driving information; determining a lateral distance between the reference lane line and the target vehicle at the end of the preset update duration according to lane line equations of the reference lane lines on both sides of the target vehicle to obtain a left lateral distance and a right lateral distance; normalizing the left lateral distance and the right lateral distance to obtain a relative lateral distance; fitting the curve of the historical trajectory of the target vehicle according to the relative lateral distance and the second driving distance to obtain a third target historical trajectory equation.

[0021] In some embodiments, in the standard lane state, there are reference lane lines on both sides of the target vehicle, and determining whether the target vehicle is in a wide curve driving state based on the lane line state and the vehicle driving information includes: when the lane line state of the target vehicle is in the standard lane state, calculating the lane curvature of the reference lane line; if the lane curvature is greater than a preset curvature threshold and the lane line state of the target vehicle is in the standard lane state within a second preset time length, determining that the target vehicle is in a wide curve driving state.

[0022] In some embodiments, the calculation of the lane curvature of the reference lane line includes: determining the farthest effective longitudinal coordinate of the target vehicle based on the lane line information of the reference lane line; calculating the lane line slopes corresponding to the reference lane lines on both sides at the farthest effective longitudinal coordinate based on the lane line equations of the reference lane lines on both sides of the target vehicle; calculating the lane curvature based on the lateral distance between the reference lane lines on both sides and the target vehicle and the lane line slope.

[0023] In some embodiments, the method further includes: when the driving state of the target vehicle does not belong to the driving state of crossing the line, the driving state along the line, the lane changing driving state and the driving state of a large curve, determining that the driving state of the target vehicle belongs to the driving state along the steering wheel trajectory.

[0024] According to a second aspect of the present application, a driving state prediction device is provided, the device comprising:

[0025] A data acquisition module, used to acquire vehicle driving information and lane line information of a target vehicle;

[0026] A driving state determination module is used to determine the driving state of the target vehicle based on the lane line based on the vehicle driving information and the lane line information.

[0027] According to a third aspect of the present application, a vehicle-mounted terminal is provided, comprising a processor and a memory, wherein the memory stores an application program, and the processor is used to run the application program in the memory to implement the driving state prediction method provided in an embodiment of the present application.

[0028] According to a fourth aspect of the present application, a vehicle is provided, comprising the vehicle-mounted terminal provided by the third aspect of the present application.

[0029] According to the fifth aspect of the present application, a computer-readable storage medium is provided, which stores a computer program, and the computer program is suitable for loading by a processor to execute the steps in any driving state prediction method provided in the embodiments of the present application.

[0030] According to the sixth aspect of the present application, a computer program product is provided, which includes a computer program, and the computer program is stored in a computer-readable storage medium; when the processor of a vehicle-mounted terminal reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the vehicle-mounted terminal executes the steps in the driving state prediction method provided in an embodiment of the present application.

[0031] In the driving state prediction method, device, vehicle-mounted terminal, vehicle and storage medium of the embodiment of the present application, the vehicle driving information and lane line information of the target vehicle are obtained; based on the vehicle driving information and lane line information, the driving state of the target vehicle based on the lane line is determined. In this way, the embodiment of the present application can determine the driving state of the target vehicle only based on the vehicle driving information and lane line information of the target vehicle, without relying on complex modeling or network construction, and establish a connection between the vehicle and environmental information through the vehicle driving information and lane line information of the target vehicle, and accurately obtain the relationship between the target vehicle and the lane line in the actual driving scene, so as to achieve accurate determination of the driving state of the target vehicle in the actual driving scene on the basis of low calculation amount, thereby improving the driving state prediction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 This is a schematic diagram of an implementation scenario of a driving state prediction method provided in an embodiment of the present application;

[0034] Figure 2 It is a flow chart of a driving state prediction method provided in an embodiment of the present application;

[0035] Figure 3a It is a schematic diagram of a vehicle coordinate system of a driving state prediction method provided in an embodiment of the present application;

[0036] Figure 3b It is a trajectory prediction schematic diagram of a driving state prediction method provided in an embodiment of the present application;

[0037] Figure 4 It is a specific flow chart of a driving state prediction method provided by an embodiment of the present application;

[0038] Figure 5 is a schematic diagram of the structure of a driving state prediction device provided in an embodiment of the present application;

[0039] Figure 6 It is a structural diagram of the vehicle-mounted terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0041] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0042] The embodiment of the present application provides a driving state prediction method, device, vehicle-mounted terminal, vehicle and storage medium. The driving state prediction device can be integrated in an electronic device, which can be a server or a terminal.

[0043] Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, network acceleration services (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. Terminals may include but are not limited to mobile phones, computers, intelligent voice interaction devices, smart home appliances, vehicle-mounted terminals, aircraft, etc. Terminals and servers can be directly or indirectly connected via wired or wireless communications, and this application does not limit this.

[0044] Among them, the vehicle-mounted terminal can be integrated in a vehicle, and the vehicle can be a fuel vehicle, a plug-in hybrid vehicle or a new energy vehicle, etc. This application does not make specific limitations on this.

[0045] See also Figure 1 , taking the driving state prediction device integrated into the vehicle terminal as an example, Figure 1 A schematic diagram of an implementation scenario of the driving state prediction method provided in an embodiment of the present application, wherein the vehicle-mounted terminal can be integrated on a vehicle, and the vehicle-mounted terminal can obtain vehicle driving information and lane line information of the target vehicle; based on the vehicle driving information and lane line information, determine the driving state of the target vehicle based on the lane line.

[0046] It should be noted that Figure 1The schematic diagram of the implementation environment scenario of the driving state prediction method shown is only an example. The implementation environment scenario of the driving state prediction method described in the embodiment of the present application is to more clearly illustrate the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided by the embodiment of the present application. It is known to those skilled in the art that with the evolution of data processing and the emergence of new business scenarios, the technical solution provided by the present application is also applicable to similar technical problems.

[0047] The solutions provided by the embodiments of the present application are specifically described by the following embodiments. It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.

[0048] This embodiment will be described from the perspective of a driving state prediction device, which can be specifically integrated in a vehicle-mounted terminal.

[0049] See also Figure 2 , Figure 2 : is a flow chart of a driving state prediction method provided in an embodiment of the present application. The driving state prediction method comprises:

[0050] Step S101, obtaining vehicle driving information and lane line information of the target vehicle.

[0051] Among them, the target vehicle may be the vehicle for which the driving state is currently being predicted, that is, it may be referred to as the self-vehicle for short. The driving state may be the state of the target vehicle driving on the road, that is, the state of the self-vehicle driving on the road, for example, it may include driving states such as driving on the line, changing lanes, driving along the line, driving on a large curve, and driving along the steering wheel track. The vehicle driving information may be information collected during the driving process of the target vehicle, and may be used to describe the driving state of the target vehicle, for example, it may include information such as the driving speed, acceleration, heading angle, and front and rear wheelbase of the target vehicle. The driving speed may be the speed of the target vehicle, and the lane line information may be information describing the lane line of the lane where the target vehicle is located. Visual perception technology may be used to obtain relevant information about the lane lines on both sides of the target vehicle. For example, a visual perception sensor can be used to collect lane line data around the vehicle. In general, each frame of vision can detect the lane line equations of four lane lines. The four lane lines are the left lane line of the left lane, the left lane line of the current lane, the right lane line of the current lane, and the right lane line of the right lane. According to their positional relationship relative to the current lane, the positions of the four lane lines can be briefly described as the left-left lane line, the left lane line, the right lane line, and the right-right lane line. The shape and specific position of each lane line can be expressed as a cubic curve in the vehicle coordinate system of the target vehicle as follows:

[0052] y=a0+a1x+a2x 2+a3x 3 ,x∈[0,x end ]

[0053] Among them, x end is the farthest effective distance of the lane line in the x-axis direction. The cubic curve contains the constant term coefficient (a0), the first-order term coefficient (a1), the second-order term coefficient (a2) and the third-order term coefficient (a3). Among them, a0 can be expressed as the lateral distance from the center of the rear axle of the vehicle to the lane line, which can show the lateral distance between the current position of the vehicle and the lane line. a1 is tan(θ), where θ is the angle between the X-axis of the vehicle coordinate system of the vehicle and the lane line, the left deviation is positive, and the right deviation is negative. a2 is K / 2, that is, half of the curvature of the lane line, and a3 can be k / 6, where k can be the curvature change rate of the lane line. Each lane line can also have additional type attributes, for example, it can include lane line types such as solid line, dashed line and curb.

[0054] The vehicle coordinate system of the target vehicle can be expressed in many ways. For example, please refer to Figure 3a , Figure 3a It is a schematic diagram of a vehicle coordinate system of a driving state prediction method provided in an embodiment of the present application. The vehicle coordinate system can be a two-dimensional Cartesian coordinate system established with the target vehicle's own vehicle forward direction as the x-axis (vertical axis), the left direction of the own vehicle as the y-axis (horizontal axis), and the center of the rear axle of the own vehicle as the origin, and the unit can be meters.

[0055] Among them, the driving state on the line can be a driving state in which the vehicle is driving on the lane line, the lane changing driving state can be a driving state in which the vehicle is changing lanes, the driving state along the line can be a driving state in which the vehicle is driving along the lane line, the wide curve driving state can be a driving state in which the vehicle is driving on a wide curve, and the driving state along the steering wheel trajectory can be a driving state in which the vehicle is not driving along the lane line, but is driving according to the turning of the steering wheel.

[0056] Step S102, based on the vehicle driving information and the lane line information, determining the driving state of the target vehicle based on the lane line.

[0057] In this way, the embodiment of the present application obtains the vehicle driving information and lane line information of the target vehicle; based on the vehicle driving information and lane line information, the driving state of the target vehicle based on the lane line is determined. In this way, the embodiment of the present application can determine the driving state of the target vehicle only based on the vehicle driving information and lane line information of the target vehicle, without relying on complex modeling or network construction, and establishes a connection between the vehicle and environmental information through the vehicle driving information and lane line information of the target vehicle, and accurately obtains the relationship between the target vehicle and the lane line in the actual driving scene, thereby achieving accurate determination of the driving state of the target vehicle in the actual driving scene on the basis of low calculation amount, thereby improving the driving state prediction efficiency.

[0058] In some embodiments, there may be multiple ways to determine the target vehicle's driving state based on the lane line based on the vehicle driving information and the lane line information. For example, based on the lane line information, a reference lane line adjacent to the target vehicle on the lane may be determined; based on the reference lane line and the vehicle driving information, the target vehicle's driving state based on the lane line may be determined.

[0059] The reference lane line may be a lane line adjacent to the target vehicle on either side of the lane.

[0060] There are multiple ways to determine the reference lane line adjacent to the target vehicle on the lane based on the lane line information. For example, among the lane lines identified based on the lane line information, for the reference lane line on the left, if the lane line at the "left" position exists, the left lane line can be used as the reference lane line on the left side of the target vehicle. If one of the following two conditions is met, lane change to the left is prohibited on the reference lane line:

[0061] (1) There is a left lane line as the reference lane line on the left, and its type attribute is curb;

[0062] (2) There is a left lane line as the reference lane line on the left side, whose type attribute is curb, and its lateral distance from the left lane line is less than a preset distance threshold. The preset distance threshold can be set according to actual needs. For example, the lateral distance here, that is, the width of the left lane, needs to be able to accommodate the width of a vehicle so that the vehicle can change lanes. However, in fact, considering that the average driver does not necessarily drive the vehicle completely across the lane line, but at least the vehicle needs to drive over half of the width (greater than 50% to be considered to have entered the left lane). At the same time, the vehicle driving along the curb is generally separated from the curb by a certain distance. Therefore, the preset distance threshold can be set according to the values ​​of these two parts, for example, it can be set to 55% of the vehicle width + 0.2 meters.

[0063] If the left lane line of the lane where the target vehicle is located does not exist, but the left-left lane line exists, the left-left lane line can be used as the reference lane line on the left. If its type attribute is curb, changing lanes to the left is prohibited.

[0064] If both the left lane marking and the left-left lane marking do not exist, there is no reference lane marking on the left.

[0065] For the reference lane line on the right side of the target vehicle, if the right lane line exists, the right lane line is used as the reference lane line on the right side. If one of the following two conditions is met, changing lanes to the right is prohibited:

[0066] (1) There is a right lane line as the reference lane line on the right side, and its type attribute is curb;

[0067] (2) There is a right lane line as the reference lane line on the right side, its type attribute is curb, and its lateral distance from the right lane line is less than a preset distance threshold.

[0068] If the right lane line does not exist and the right-right lane line exists, the right-right lane line can be used as the reference lane line on the right side. If its type attribute is curb, changing lanes to the right is prohibited.

[0069] If both the right lane marking and the right-right lane marking do not exist, there is no reference lane marking on the right side of the target vehicle.

[0070] Optionally, the lane equations of the two reference lanes can be expressed as:

[0071] y l =a l_0 +a l_1 x+a l_2 x 2 +a l_3 x 3 ,x∈[0,x l_end ]

[0072] y r =a r_0 +a r_1 x+a r_2 x 2 +a r_3 x 3 ,x∈[0,x r_end ]

[0073] Among them, x l_end is the reference lane line y on the left l The maximum distance in the x-axis direction, x r_end is the reference lane line y on the right r The maximum distance in the x-axis direction, a l_0 is the constant term coefficient of the lane line equation of the left reference lane line, which can be expressed as the lateral distance from the center of the rear axle of the vehicle to the left reference lane line. l_1 It can represent the linear coefficient of the lane equation of the reference lane on the left. l_2 It can represent the quadratic coefficient of the lane equation of the reference lane on the left, a l_3 It can represent the cubic coefficient of the lane line equation of the reference lane line on the left, a r_0 is the constant term coefficient of the lane equation of the reference lane on the right, which can be expressed as the lateral distance from the center of the rear axle of the vehicle to the reference lane on the right. r_1 It can represent the linear coefficient of the lane equation of the reference lane on the right. r_2 It can represent the quadratic coefficient of the lane equation of the reference lane on the right, a r_3The cubic coefficient of the lane line equation of the reference lane line on the right can be expressed.

[0074] After determining the reference lane line adjacent to the target vehicle on the lane based on the lane line information, the driving state of the target vehicle based on the lane line can be determined based on the reference lane line and the vehicle driving information. There are multiple ways to determine the driving state of the target vehicle based on the lane line based on the reference lane line and the vehicle driving information. For example, a first target historical trajectory equation can be determined based on the reference lane line and the vehicle driving information, and the driving state of the target vehicle can be determined based on the first target historical trajectory equation.

[0075] The first target historical trajectory equation may be a quadratic curve equation of the historical trajectory of the target vehicle fitted based on the reference lane line and the vehicle driving information.

[0076] Among them, there are many ways to determine the first target historical trajectory equation based on the reference lane line and the vehicle driving information. For example, the first driving distance and the first lateral distance can be obtained according to the lane line equation of the reference lane line and the vehicle driving information; based on the first driving distance and the first lateral distance, the trajectory curve of the historical trajectory of the target vehicle is determined to obtain the first target historical trajectory equation.

[0077] Among them, the first driving distance is the distance traveled by the target vehicle between the first moment and the second moment, the first lateral distance is the distance between the target vehicle and the reference lane line at the second moment, the first moment can be the starting moment within the data update duration, the second moment can be the ending moment of the data update duration, the data update duration can be the duration for updating the data, and the first driving distance and the first lateral distance are obtained once within a data update duration.

[0078] Among them, there are many ways to determine the trajectory curve of the historical trajectory of the target vehicle based on the first driving distance and the first lateral distance, and obtain the first target historical trajectory equation. For example, the first angle value can be obtained; if the absolute value of the first lateral distance is less than the first preset distance threshold and the absolute value of the first angle value is less than the first preset angle threshold, then based on the first driving distance and the first lateral distance, the curve of the historical trajectory of the target vehicle is determined to obtain the first target historical trajectory equation.

[0079] Among them, the first angle value can indicate the angle between the driving direction of the target vehicle and the reference lane line at the second moment, that is, the lane line direction of the reference lane line. The first preset distance threshold can be a preset distance threshold, which is used to measure the distance between the target vehicle and the reference lane line, so that the driving state of the target vehicle can be determined. The specific value of the first preset distance threshold can be set according to actual needs, and the embodiment of the present application is not limited here. The first preset angle threshold can be a pre-set threshold, which is used to measure the direction difference between the target vehicle and the reference lane line, so that it can be used to assist in determining the driving state of the target vehicle.

[0080] Among them, if the absolute value of the first lateral distance is less than the first preset distance threshold and the absolute value of the first angle value is less than the first preset angle threshold, then based on the first driving distance and the first lateral distance, the curve of the historical trajectory of the target vehicle is determined, and there are many ways to obtain the first target historical trajectory equation. For example, the second lateral distance can be obtained, and the second lateral distance is the lane line equation through the reference lane line, and the distance between the target vehicle and the reference lane line is predicted at the preset longitudinal distance in front of the target vehicle. If the absolute value of the first lateral distance is less than the first preset distance threshold and the absolute value of the first angle value is less than the first preset angle threshold, and the second lateral distance is not greater than the second preset distance threshold, based on the first driving distance and the first lateral distance, the quadratic curve of the historical trajectory of the target vehicle is determined to obtain the first target historical trajectory equation.

[0081] The preset longitudinal distance may be a preset longitudinal distance used to assist in determining the distance relationship between the target vehicle and the reference lane line, thereby being used to determine the driving state of the target vehicle. The second preset distance threshold may be a preset distance threshold used to measure the distance between the target vehicle and the reference lane line at a preset longitudinal distance in front of the target vehicle, thereby being used to assist in determining the driving state of the target vehicle.

[0082] For example, in a specific embodiment, after the reference lane line is collected by the sensor of the target vehicle, the following steps can be used to determine the first target historical trajectory equation based on the reference lane line and the vehicle driving information:

[0083] Among them, the lane line equation of the reference lane line can be expressed as:

[0084] y c =a c_0 +a c_1 x+a c_2 x 2 +a c_3 x 3 ,x∈[0,x c_end ]

[0085] Among them, xc_end The lane equation y is the reference lane line c The maximum effective distance in the x-axis direction, a c_0 is the constant coefficient of the lane equation of the reference lane, which can be expressed as the lateral distance from the center of the rear axle of the vehicle to the adjacent reference lane. c_1 It can represent the linear coefficient of the lane equation of the reference lane. c_2 It can represent the quadratic coefficient of the lane equation of the reference lane, a c_3 The cubic coefficient of the lane line equation of the reference lane line can be expressed.

[0086] Step 1: Create an array [X i ,D i ], which can be used to store multiple sets of historical moment data of the target vehicle: the first driving distance traveled by the vehicle from the moment the data is stored (i.e. the first moment) to the current moment (i.e. the second moment), the first lateral distance of the vehicle relative to the adjacent reference lane line, and set the shortest time Th for updating historical data t_r , and the maximum storage capacity of data points D num (including the current time).

[0087] Step 2: Set the first preset distance threshold Th respectively Offset_r , the first preset angle threshold Th dir_r If the following conditions are met:

[0088] |a c_0 | <Th offset_r ,|a c_1 | <Th dir_r

[0089] That is, if the absolute value of the first lateral distance is less than the first preset distance threshold and the absolute value of the first angle value is less than the first preset angle threshold, then when the update time Th is satisfied t _r stores and records the current system time t system , and go to step 3. If the conditions are not met, the stored data points of the historical moment are cleared and not stored.

[0090] Step 3: Update the first driving distance of the stored data point. Specifically, the current driving speed v of the target vehicle can be obtained. car , get the historical time t of the stored data point at the last update last , the first driving distance is updated according to the following rules, where the larger the data subscript is, the earlier the historical time is. For example, X1 represents the first driving distance stored at the current moment, and the update rule for the first driving distance stored historically is:

[0091]

[0092] Step 4: Update the first horizontal distance stored. The update can be performed according to the following rules. The larger the data subscript, the earlier the historical time. D1 represents the first horizontal distance stored at the current moment. The update rule for the first horizontal distance stored historically is:

[0093]

[0094] Step 5: If the number of stored data points is greater than 3, but the longitudinal distance x is preset in front trend At the point where the second lateral distance between the target vehicle and the adjacent reference lane line determined based on the steering wheel trajectory is not greater than the second preset distance threshold D OffLat , we can perform curve fitting of the historical trajectory based on the historically stored data points to obtain the historical trajectory equation of the first target:

[0095] y t =a tr_0 +a tr_ 1x+a tr_2 x 2

[0096] Optionally, there may be multiple ways to determine the driving state of the target vehicle based on the lane lines based on the reference lane lines and the vehicle driving information. For example, the driving state may include a driving state of crossing the lane lines. The neighboring reference lane lines of the target vehicle may be determined among the reference lane lines, and based on the neighboring reference lane lines and the vehicle driving information, it may be determined whether the target vehicle is in a driving state of crossing the lane lines.

[0097] The neighboring reference lane line may be a lane line among the reference lane lines that is closest to the target vehicle.

[0098] There are many ways to determine the neighboring reference lane line of the target vehicle among the reference lane lines. For example, if both reference lane lines do not exist, the judgment process of the driving state of crossing the line will not be performed. At this time, there is no neighboring reference lane line processing for the target vehicle; if the target vehicle has only one reference lane line data, this reference lane line can be selected as the neighboring reference lane line for judging the driving state of crossing the line; if both reference lane lines exist, the reference lane line with a smaller lateral distance |a0| value is selected as the neighboring reference lane line.

[0099] In some embodiments, there are multiple ways to determine whether the target vehicle is in a driving state of pressing the line based on the neighboring reference lane line and the vehicle driving information. For example, the first target historical trajectory equation can be fitted, and the target vehicle can be determined whether it is in a driving state of pressing the line based on the first target historical trajectory equation. For example, in the process of determining the driving state of pressing the line, the first target historical trajectory equation can be the first historical trajectory equation, and the first historical trajectory equation can be the first target historical trajectory equation determined based on the neighboring reference lane line. Specifically, the quadratic curve of the historical trajectory of the target vehicle can be fitted based on the neighboring reference lane line and the vehicle driving information to obtain the first historical trajectory equation; the first predicted lateral distance of the target vehicle is calculated based on the first historical trajectory equation, the driving speed in the vehicle driving information, and the first preset prediction duration; when the first predicted lateral distance is within the distance range corresponding to the first preset distance threshold, it is determined that the target vehicle is in a driving state of pressing the line.

[0100] Among them, the first historical trajectory equation can be the equation of the quadratic curve of the historical trajectory of the target vehicle fitted based on the neighboring reference lane line during the judgment process of the line-crossing driving state. The first preset prediction time can be a preset time, which can be used to calculate the first predicted lateral distance. The first predicted lateral distance can be the lateral distance between the position where the target vehicle is traveling after the first preset prediction time and the neighboring reference lane line. The first preset distance threshold can be a preset distance threshold, and the specific value can be set according to the actual situation. For example, when the first preset distance threshold is Th Offset _r, the distance range corresponding to the first preset distance threshold may be [-Th Offset _r,Th Offset _r].

[0101] There are many ways to obtain the first historical trajectory equation by fitting the quadratic curve of the historical trajectory of the target vehicle according to the neighboring reference lane line and the vehicle driving information. For example, in the same way as determining the first target historical trajectory equation, the first driving distance of the target vehicle and the first lateral distance and the first angle value between the target vehicle and the neighboring reference lane line can be obtained according to the lane line equation of the neighboring reference lane line and the vehicle driving information; if the state in which the absolute value of the first lateral distance is less than the first preset distance threshold and the absolute value of the first angle value is less than the first preset angle threshold continues to exceed the first preset time length, and at the preset longitudinal distance in front of the target vehicle, the second lateral distance between the target vehicle and the neighboring reference lane line is not greater than the second preset distance threshold, based on the first driving distance and the first lateral distance, the quadratic curve of the historical trajectory of the target vehicle is fitted to obtain the first historical trajectory equation.

[0102] Among them, in the process of judging the lane-crossing driving state, the first angle value can be an angle indicating the driving direction of the target vehicle and the reference lane line, that is, indicating the lane line direction of the adjacent reference lane line.

[0103] For example, in a specific embodiment, when the lane line information of the current frame collected by the target vehicle through the sensor and the lane line information of the previous frame both have adjacent reference lane lines, it is necessary to perform a judgment process on the driving state of the lane crossing. The specific judgment process refers to the following steps:

[0104] Among them, the lane line equation of the neighboring reference lane line is:

[0105] y c =a c_0 +a c_1 x+a c_2 x 2 +a c_3 x 3 ,x∈[0,x c_en d]

[0106] Among them, x c_end The lane equation y of the neighboring reference lane c The maximum effective distance in the x-axis direction, a c_0 is the constant coefficient of the lane equation of the nearest reference lane, which can be expressed as the lateral distance from the center of the rear axle of the vehicle to the nearest reference lane. c_1 It can represent the linear coefficient of the lane equation of the nearest reference lane. c_2 It can represent the quadratic coefficient of the lane equation of the nearest reference lane, a c_3 The cubic coefficient of the lane line equation that can represent the neighboring reference lane line.

[0107] Step 1: Create an array [X i ,D i ], which can be used to store multiple sets of historical moment data of the target vehicle: the first travel distance traveled by the vehicle from the time the data is stored to the current moment, the first lateral distance of the vehicle relative to the adjacent reference lane line, and set the shortest time Th for updating historical data t_ r, and the maximum storage capacity of data points D num (including the current time).

[0108] Step 2: Set the first preset distance threshold Th respectively Offset_r , the first preset angle threshold Th dir_r If the following conditions are met:

[0109] |a c_0 | <Th offset_r |a c_1 | <Thdir_r

[0110] That is, if the absolute value of the first lateral distance is less than the first preset distance threshold and the absolute value of the first angle value is less than the first preset angle threshold, then when the update time Th is satisfied t_r Store and record the current system time t under the request system , and go to step 3. If the conditions are not met, the stored data points of the historical moment are cleared and not stored.

[0111] Step 3: Update the first driving distance of the stored data point. Specifically, the current driving speed v of the target vehicle can be obtained. car , get the historical time t of the stored data point at the last update last , the first driving distance is updated according to the following rules, where the larger the data subscript is, the earlier the historical time is. For example, X1 represents the first driving distance stored at the current moment, and the update rule for the first driving distance stored historically is:

[0112]

[0113] Step 4: Update the first horizontal distance stored. The update can be performed according to the following rules. The larger the data subscript, the earlier the historical time. D1 represents the first horizontal distance stored at the current moment. The update rule for the first horizontal distance stored historically is:

[0114]

[0115] Step 5: Perform different status processing according to the current driving status of the target vehicle.

[0116] 1. The target vehicle has entered the driving state of pressing the line: if the number of stored data points is 0, the driving state of pressing the line is exited, and the judgment process of the driving state of pressing the line is ended; otherwise, the driving state of pressing the line is maintained, and the judgment process of the driving state of pressing the line is ended.

[0117] 2. The target vehicle has not entered the state of driving on the line: If the number of stored data points is less than 3, the state of driving on the line can be maintained, and the judgment process of driving on the line ends; if the number of stored data points is greater than 3, but the longitudinal distance x is preset in front trend At the point where the lateral distance between the target vehicle and the adjacent reference lane line determined based on the steering wheel trajectory is greater than the second preset distance threshold D OffLat , the target vehicle is kept in a state of not crossing the line, and the judgment process of the state of crossing the line is completed.

[0118] If the number of stored data points is greater than 3, but the longitudinal distance x is preset in front trendThe lateral distance between the target vehicle and the adjacent reference lane line is not greater than the second preset distance threshold D OffLat , then the target vehicle's line-crossing data can be calculated:

[0119] (1) Perform curve fitting of the historical trajectory based on the historically stored data points to obtain the first historical trajectory equation:

[0120] y t =a tr_0 +a tr_1 x+a tr_2 x 2

[0121] Among them, the first history trajectory equation y in the quadratic curve form t In the equation, the quadratic coefficient a tr_2 Can represent the curvature of the vehicle, a one-time coefficient a tr_1 It can indicate the direction of vehicle travel.

[0122] The stored data points [X i ,D i The average value of the first travel distance and the first lateral distance in The coefficient a of the first historical trajectory equation tr_1 The calculation result can be expressed as:

[0123]

[0124] The constant coefficient a of the first history trajectory equation tr_0 And the quadratic coefficient can be a tr_2 The calculation result can be expressed as:

[0125]

[0126] Among them, num can be represented as the number of data points currently stored.

[0127] (2) Based on the current vehicle speed v car and the first preset prediction duration T pre , calculated at T pre ×v car At , the expected first predicted lateral distance is:

[0128] D pre =a tr_0 +a tr_1 *(T pre *v car )+a tr_2 *(T pre *v car ) 2

[0129] If the first predicted lateral distance D pre Belongs to the first preset distance threshold Th Offset_r The corresponding distance range [-Th Offset_r ,Th Offset_r ] and lasts for a preset time Th k_time ,Th k_time The specific value of can be set according to the actual situation, for example, it can be 2 seconds, 3 seconds, etc. The number of historically stored data points num is not less than 3, and the first predicted lateral distance D pre All within the range [-Th Offset_r ,Th Offset_r ], it is determined that the target vehicle has entered the line-crossing driving state, otherwise the timing is reset.

[0130] For another example, when the target vehicle passes through the previous frame of lane line information collected by the sensor, there is no adjacent reference lane line. When the current frame has an adjacent reference lane line, the lane line equation of the adjacent reference lane line can be expressed as:

[0131] y c =a c_0 +a c_1 x+a c_2 x 2 +a c_3 x 3 ,x∈[0,x c_end ]

[0132] If satisfied:

[0133] |a c_0 | <Th offset_r ,|a c_1 | <Th dir_r

[0134] And the longitudinal distance x is preset in front of the target vehicle trend At the point where the lateral distance between the target vehicle and the adjacent reference lane line determined based on the steering wheel trajectory is less than the second preset distance threshold D OffLat , it is determined that the target vehicle is in a driving line crossing state.

[0135] For another example, when the target vehicle has an adjacent reference lane line in the previous frame of lane line information collected by the sensor, but there is no adjacent reference lane line in the current frame, it is determined that the target vehicle is not in a lane-crossing driving state.

[0136] In this way, the embodiment of the present application predicts the driving state by predicting the driving trajectory based on historically stored data points, which has higher stability and accuracy compared with the method of directly comparing the threshold. At the same time, when fitting the driving trajectory curve based on the data points of driving in the lane, the quadratic curve is used for fitting, the vehicle driving direction is determined based on the linear term coefficient in the quadratic curve, and the vehicle curvature is determined using the quadratic term coefficient. Compared with the conventional method of directly using the cubic curve, the prediction effect is less affected by data errors, can eliminate the back-and-forth oscillation of the data, has higher stability and accuracy, and can thus improve the accuracy of the driving state prediction.

[0137] In one embodiment, there may be multiple ways to determine the driving state of the target vehicle based on the lane line based on the reference lane line and the vehicle driving information. For example, the driving state may include at least one of a driving state along the line, a lane change driving state, and a large curve driving state. In this way, the lane line state of the target vehicle may be determined based on the reference lane line. The lane line state includes a standard lane state and a non-standard lane line state. Based on the lane line state and the vehicle driving information, it is determined whether the target vehicle belongs to at least one of the driving states along the line, the lane change driving state, and the large curve driving state.

[0138] Among them, the standard lane state may refer to the existence of valid lane lines on both sides of the target vehicle, and the lane width between the valid lane lines is within the preset lane width range, and the preset lane width range may be the width range of a normal lane. If at least one of the two reference lane lines does not exist, at this time, the state of the reference lane line of the target vehicle may be determined to be an "invalid state", which may also be referred to as a non-standard lane state. In this way, when there are reference lane lines on both sides of the target vehicle, the lane width between the reference lane lines may be calculated based on the lane line equations of the reference lane lines on both sides. If the lane width is within the preset lane width range, it is determined that the lane line state of the target vehicle belongs to the standard lane state. If not, it is determined that the lane line state of the target vehicle belongs to the non-standard lane state.

[0139] There may be a variety of ways to determine the lane line state of the target vehicle based on the reference lane line. For example, if the target vehicle lacks the reference lane line on at least one side, it can be determined that the lane line state of the target vehicle belongs to a non-standard lane state. If the target vehicle has reference lane lines on both sides and the lane width between the reference lane lines is within a preset lane width range, it is determined that the lane line state of the target vehicle belongs to a standard lane state. If the target vehicle has reference lane lines on both sides and the lane width between the reference lane lines is not within the preset lane width range, it is determined that the lane line state of the target vehicle belongs to a non-standard lane state.

[0140] When there are reference lane lines on both sides of the target vehicle, the lane width validity judgment can be performed to determine whether the lane line state of the target vehicle belongs to the standard lane state. Specifically, the lane width between the reference lane lines can be calculated based on the lane line equations of the reference lane lines on both sides. If the lane width is within the preset lane width range, it is determined that the lane line state of the target vehicle belongs to the standard lane state. If not, it is determined that the lane line state of the target vehicle belongs to the non-standard lane state. For example, the lane line equation based on the reference lane lines on both sides of the target vehicle is as follows:

[0141] y l =a l_0 +a l_1 x+a l_2 x 2 +a l_x x 3 ,x∈[0,x l_end ]

[0142] y r =a r_0 +a r_1 x+a r_2 x 2 +a r_3 x 3 ,x∈[0,x r_end ]

[0143] Lane line detection can be achieved through image acquisition. The image can only clearly obtain the lane lines within a certain distance ahead. Therefore, the maximum distance of the lane line recognized by the image, or the length of the lane line ahead is not long, x l_end 、x r_end Indicates the farthest x-coordinate of the reference lane line. Sets the farthest effective distance X of the x-coordinate of the reference lane lines on both sides of the target vehicle effi , the maximum effective distance of the lane where the target vehicle is located in the x direction is Th x_end 、x l_end 、x r_end The minimum value of three numbers, among which Th x_end To set a fixed threshold greater than 0, the specific value of the threshold can be set according to the actual situation. The farther the distance between the reference lane line and the current position of the target vehicle, the greater the error between the lane line recognized by the image and the actual lane line. The lane line data within a certain distance can be considered to have a higher accuracy, while the lane line data at a longer distance has a lower accuracy. This dividing point is the threshold Th. x_end Therefore, the process of determining the lane width validity may include the following steps:

[0144] Step 1: The lane width between the reference lane lines on both sides can be preliminarily determined to quickly filter out the obviously invalid lane lines. Specifically, the width threshold range boundary [B min ,B max ], if not satisfied (a l_0 –a r_0 )∈[B min , B max ], then the lane line state of the target vehicle is "non-standard lane state". If it is satisfied, proceed to step 2.

[0145] Step 2: Starting from the target vehicle's ego position x = 0, select a point x every 5 m until x effi For each x value, the corresponding x-axis position of point A and point B can be calculated on the left and right reference lane lines, and the slope K of the corresponding reference lane line. A , K B , passing through point A, with a slope Draw a straight line that intersects the reference lane line on the right at point B, and calculate the slope k of the lane line at the corresponding point B′ , replace the parameters at the original point B, repeat the above steps several times to complete the iteration. Finally, point B is updated to point B″.

[0146] The lane width corresponding to the x value is calculated as the distance between point A and point B', and the lane width W at different x points is obtained. x (x=0, 5, 10, ...X effi ). The lane width corresponding to the vehicle position x = 0 is recorded as W curr .

[0147] Step 3: Determine the preset lane width range, for example, set the width change rate threshold Th at different distances in front of the vehicle min ,Th max ,Th rate , and the distance threshold T hx_b Among them, Th min ,Th max In fact, it is the ratio of the minimum lane width, maximum lane width and lane width at the current position. rate It is mainly based on the normal lane width change (the scene of obvious width change mainly occurs when there are merging / exiting lanes, or the number of lanes changes from a few to many, or from many to a few, etc.), the lane width change ratio threshold is set, and the lane width recognized by the image is added. Distance threshold T hx_bIn order to ensure that the lane width is within the minimum and maximum width range at a certain distance in front of the vehicle, this threshold can be determined according to the speed of the target vehicle. The higher the speed, the greater the threshold. Thus, the preset lane width range at different x coordinates can be calculated. The specific calculation is as follows:

[0148]

[0149]

[0150] Among them, Width min It can be the minimum lane width in the preset lane width range. max It can be the maximum lane width in the preset lane width range.

[0151] Step 4: Determine the validity of the lane width. Specifically, for the multiple x points set in step 2, determine the lane width W x Does it satisfy w x ∈[Width min ,Width max ], if one condition is not satisfied, the lane line state of the target vehicle is “non-standard lane state”, otherwise it is “standard lane state”.

[0152] Among them, there can be multiple ways to determine whether the target vehicle is in a driving state along the line or a lane changing driving state based on the lane line state and the vehicle driving information. For example, when the lane line state belongs to a non-standard lane state, based on the vehicle driving information and the lane line information of the reference lane line, it is determined whether the target vehicle is in a driving state along the line; when the lane line state belongs to a standard lane state, based on the vehicle driving information and the lane line information of the reference lane line, it is determined whether the target vehicle is in a lane changing driving state.

[0153] There are multiple ways to determine whether the target vehicle is in a state of traveling along the line based on the vehicle driving information and the lane line information of the reference lane line. For example, method 1 can be used to determine whether the target vehicle is in a state of traveling along the line based on the vehicle driving information and the lane line information of the reference lane line. Specifically, in the process of judging the state of traveling along the line, the first target historical trajectory equation includes the second historical trajectory equation. In the process of judging the state of traveling along the line, a new first preset distance threshold and a first preset angle threshold can be set, so that the first driving distance of the target vehicle and the target vehicle can be obtained based on the lane line information of the reference lane line and the vehicle driving information. a first lateral distance and a first angle value between the target vehicle and each reference lane line; if the absolute value of the first lateral distance is less than the first preset distance threshold and the absolute value of the first angle value is less than the first preset angle threshold for a period of time exceeding a preset time, based on the first driving distance and the first lateral distance, construct a quadratic curve of the historical trajectory of the target vehicle to obtain a second historical trajectory equation; based on the second historical trajectory equation, the driving speed in the vehicle driving information and the second preset prediction time, calculate the second predicted lateral distance of the target vehicle; when the second predicted lateral distance is within the preset lateral distance range, determine that the target vehicle is in a state of traveling along the current reference lane line.

[0154] Specifically, the same steps as steps 1 to 4 in the process of judging the driving state of crossing the line can be performed to set a new first preset distance threshold Th Offset_r , the first preset angle threshold Th dir_r , to store the data points and obtain the final array of historical data points [X i ,D i ], including a first driving distance and a first lateral distance.

[0155] When the number of data points stored at the historical moment is less than 3, the judgment process of the driving status along the line is exited, and it is determined that the target vehicle is not driving along the reference lane line on the current side.

[0156] When the number of data points storing historical moments is not less than 3, a curve fitting is performed based on the first travel distance and the first lateral distance in the data points, and the second historical trajectory equation can be expressed as:

[0157] y t =a tr_0 +a tr_1 x+a tr_2 x 2

[0158] Calculate the first driving distance and the first lateral distance [X i ,D i The average value of The coefficient a of the first-order term of the second historical trajectory equationtr_1 The calculation result can be expressed as:

[0159]

[0160] The constant coefficient a of the second history trajectory equation tr_0 and the quadratic coefficient can be a tr_2 The calculation result can be expressed as:

[0161]

[0162] According to the current vehicle speed v car and the second preset prediction duration T pre , calculate the longitudinal distance T pre ×v car At , the expected second predicted lateral distance is:

[0163] D pre =a tr_0 +a tr_1 *(T pre *v car )+a tr_2 *(T pre *v car ) 2

[0164] If the second predicted lateral distance D pre In the range [-|2×a tr_0 |,0.5] (processing the reference lane line on the left) or [-0.5,|2×a tr_0 |] (processing the right reference lane line), it can be determined that the target vehicle is in a driving state along the reference lane line on this side, and the confidence deviation can be calculated:

[0165] c=|D pre -a tr_0 |

[0166] If the calculation results of the reference lane lines on both sides are both in the along-line driving state, it can be determined that the target vehicle is in the along-line driving state along the lane line on the side with the smaller confidence deviation.

[0167] Optionally, method 2 can be used to determine whether the target vehicle is in a state of driving along the line based on the vehicle driving information and the lane line information of the reference lane line. Specifically, based on the vehicle driving information, a curve of the historical trajectory of the target vehicle in the vehicle coordinate system of the target vehicle can be obtained to obtain a second target historical trajectory equation; based on the second target historical trajectory equation and the lane line equation of the reference lane line, it is determined whether the target vehicle is in a state of driving along the line along the current reference lane line.

[0168] Among them, based on the second target historical trajectory equation and the lane line equation of the reference lane line, there can be multiple ways to determine whether the target vehicle is in a state of traveling along the current reference lane line. For example, based on the second target historical trajectory equation and the lane line equation of the reference lane line, the width distance value between the target vehicle and the reference lane line can be calculated; when the width distance value is within a preset width distance range, it is determined that the target vehicle is in a state of traveling along the current reference lane line.

[0169] Specifically, similar to steps 1 to 4 in the process of determining the driving state of crossing the line, a new first preset distance threshold Th may be set. Offset_r , the first preset angle threshold Th dir_r , to store the data points and obtain the final array of historical data points [Xi, Di].

[0170] The historical driving trajectory of the target vehicle can be fitted based on the historical data points [Xi, Di] obtained from the vehicle driving information. For example, please refer to Figure 3b , Figure 3b : is a trajectory prediction schematic diagram of a driving state prediction method provided by an embodiment of the present application. Trajectory fitting can be performed based on the stored data points at historical moments to predict the trajectory of the target vehicle, so that the historical driving trajectory of the vehicle can be converted to the vehicle coordinate system of the target vehicle to obtain the second target historical trajectory equation y h ,as follows:

[0171] y h =a h_0 +a h_1 x+a h_2 x 2 +a h_3 x 3

[0172] The lane line equation for the reference lane line on one side used for calculation can be expressed as:

[0173] y=a0+a1x+a2x 2 +a3x 3

[0174] The second target history trajectory equation y h The lane line equation is regarded as the lane line equation, and compared with the lane line equation of the reference lane line. The processing steps are the same as the steps of judging the lane width validity when judging the lane line state, wherein a new threshold Th needs to be set x_end and width threshold range boundary [B min ,B max ].

[0175] If the above judgment result is "standard lane state", it can be determined that the target vehicle is in a driving state along the reference lane line on the current side, and the confidence deviation can be calculated:

[0176] C=|a h_0 -a0|*|a h_2 -a2|

[0177] If the calculation results of the reference lane lines on both sides are both in the along-line driving state, it can be determined that the target vehicle is in the along-line driving state along the lane line on the side with the smaller confidence deviation.

[0178] Optionally, when judging the driving status along the line, method one and method two can be calculated at the same time. If both method one and method two calculate that the target vehicle is in a driving state along the line and is not along the reference lane line on the same side, the judgment result of method one can be selected as the final judgment result.

[0179] In one embodiment, there are multiple ways to determine whether the target vehicle is in a lane changing state based on the vehicle driving information and the lane line information of the reference lane line. For example, in the standard lane state, there are reference lane lines on both sides of the target vehicle. Based on the lane line equation of the reference lane line, a second angle value can be obtained. The second angle value indicates the angles between the reference lane lines on both sides of the target vehicle and the driving direction of the target vehicle. If the absolute values ​​of the second angle values ​​are less than the corresponding second preset angle thresholds, and the continuous duration of the target vehicle in the standard lane state exceeds the first preset duration, based on the vehicle driving information and the lane line information, a curve of the historical trajectory of the target vehicle is obtained to obtain a third target historical trajectory equation. Based on the third target historical trajectory equation, it is determined whether the target vehicle is in a lane changing state.

[0180] Among them, there are many ways to obtain the curve of the historical trajectory of the target vehicle based on the vehicle driving information and the lane line information, and to obtain the third target historical trajectory equation. For example, the second driving distance of the target vehicle within the preset update time period can be obtained based on the vehicle driving information, and the lateral distance between the reference lane line and the target vehicle at the end of the preset update time period is determined according to the lane line equation of the reference lane line on both sides of the target vehicle, and the left lateral distance and the right lateral distance are obtained. The left lateral distance and the right lateral distance are normalized to obtain the relative lateral distance, and the curve of the historical trajectory of the target vehicle is fitted according to the relative lateral distance and the second driving distance to obtain the third target historical trajectory equation.

[0181] Among them, the second driving distance can be the driving distance of the target vehicle collected within the preset update time, the left lateral distance can be the lateral distance between the reference lane line on the left and the target vehicle, and the right lateral distance can be the lateral distance between the reference lane line on the right and the target vehicle.

[0182] Optionally, based on the lane line equation of the reference lane line, a third angle value of the reference lane lines on both sides of the target vehicle relative to the target vehicle can be obtained. If the absolute value of the third angle value is less than a third preset angle threshold, and the continuous time that the target vehicle belongs to the standard lane state exceeds the preset time, the quadratic curve of the historical trajectory of the target vehicle can be obtained based on the vehicle driving information and lane line information to obtain the third target historical trajectory equation.

[0183] Among them, there are multiple ways to determine whether the target vehicle belongs to the lane changing driving state based on the third target historical trajectory equation. For example, based on the third target historical trajectory equation, it can be determined whether the target vehicle belongs to one of the multiple lane changing driving sub-states included in the lane changing driving state. The lane changing driving sub-states include: driving along the standard lane, changing lanes, pre-completed lane change, completed lane change and failed lane change.

[0184] In a specific embodiment, when the reference lane line of the target vehicle is in the "standard lane state" and is not judged as a line-crossing driving state, the lane change driving state can be calculated to predict whether the target vehicle is about to exit the lane and the direction of exit.

[0185] Step 1: Store the data of “standard lane status”.

[0186] Get the lane line equations of the left and right reference lane lines. You can use the one-time coefficient a in the lane line equation of the reference lane line l_1 、a r_1 , determine the direction of the reference lane lines on both sides of the target vehicle relative to the lane lines of the target vehicle, that is, the third angle value, and set the preset time length Th for the "standard lane state" to be stable s_ t, new preset distance threshold Th Offset_r , the threshold of the lane line direction (i.e., the third preset angle threshold) Th dir_r , the reference lane lines on both sides exist and are continuous Th s_t When the time is "standard lane status" and the following conditions are met:

[0187] |a l_1 | <Th dir_r ,|a r_1 | <Th dir_r

[0188] That is, if the absolute value of the third angle value is less than the third preset angle threshold, and the continuous duration of the target vehicle in the standard lane state exceeds the preset duration, the data of the "standard lane state" begins to be stored:

[0189] (1) Create an array [Xi, Di] to store historical data: the second driving distance relative to the current position, and the corresponding lateral distance of the target vehicle relative to the reference lane line, and set the shortest time Th for updating historical data t_r , and the maximum storage capacity of data points D num (including the current time).

[0190] (2) When the update time Th is met t_r Update the data points of the stored historical data at the request of the system, and store the current system time t system , and proceed to the next step.

[0191] (3)Data update.

[0192] Update the second driving distance: Get the current driving speed v of the vehicle car , get the historical time t stored at the last update last , and is updated according to the following rules, where the larger the data subscript, the earlier the historical time, and X1 represents the second driving distance stored at the current moment:

[0193]

[0194] Update the relative lateral distance within the lane according to the following rules:

[0195]

[0196] Among them, a l _0 represents the left lateral distance of the left reference lane line, that is, the constant term coefficient of the lane line equation of the left reference lane line, a r _0 represents the right lateral distance of the reference lane line on the right, that is, the constant coefficient of the lane line equation of the reference lane line on the right. Normalize the left lateral distance and the right lateral distance to obtain the relative lateral distance D i , so the D calculated after normalization is i The range can be kept constant at [-1,1], avoiding the impact of lane width detection errors at different times and further improving the accuracy of driving state prediction.

[0197] Step 2: Driving trajectory fitting.

[0198] When the number of data points of the stored historical data is not less than 3, the driving trajectory of the target vehicle in the standard lane state can be fitted according to the relative lateral distance and the second driving distance in the stored data points, and the following quadratic curve is obtained by fitting, that is, the third target historical trajectory equation:

[0199] y t =a tr_0 +atr_1 x+a tr_2 x 2

[0200] Among them, the second driving distance and the relative lateral distance [X i ,D i The average value of The first-order coefficient a of the third target historical trajectory equation tr_1 The calculation result can be expressed as:

[0201]

[0202] The constant coefficient a of the third target history trajectory equation tr_0 And the quadratic coefficient can be a tr_2 The calculation result can be expressed as:

[0203]

[0204] Among them, the historical data points and the fitted ego vehicle predicted driving trajectory can be as follows Figure 3b shown.

[0205] Step 3: Calculation of lane change driving status.

[0206] The lane change driving state includes the following five lane change driving sub-states:

[0207]

[0208] When the target vehicle is driving along the standard lane, if the number of stored data points is not less than 3, enter the judgment of other sub-states; otherwise, exit the calculation and output the sub-state "driving along the standard lane";

[0209] Set the prediction time T pre , and according to the current speed v of the vehicle car , calculate the longitudinal distance T pre ×v car At , the expected predicted lateral distance is:

[0210] D pre =a tr_0 +a tr_1 *(T pre *v car )+a tr_2 *(T pre *V car ) 2

[0211] Processing expected predicted lateral distance D pre , set the state duration threshold Th k_time :

[0212] A. If D pre In the range [-∞, -1], and D1 in the range [-1, Th w_st ], and the continuous time Th k_time If the number of data points of the stored historical data is not less than 3, and the reference lane line is not prohibited from changing lanes to the left, the lane-changing driving sub-state "lane changing" can be output, and the direction is changing lanes to the left.

[0213] B. If D pre In the range [1, +∞], and D1 is in the range [Th w_st ,1], and continuous Th k_time If the number of points stored in the historical data is not less than 3 within the time period, and the reference lane line is not prohibited from changing lanes to the right, the lane change driving sub-state "lane changing" is output, and the direction is changing lanes to the right.

[0214] When the target vehicle is in the state of changing lanes, the target vehicle crosses the lane line on the corresponding side, that is, the latest data D1 and D2 stored in the current frame meet:

[0215] D1*D2<0,D1≠±1

[0216] The driving state of the target vehicle can be set to the lane change driving sub-state of "lane change pre-completion", and at the same time, the lateral distance of the data point stored at the historical moment can be updated:

[0217]

[0218] You can set the state exit prediction time T pre_c , set the time threshold Th required for the state to exit c_time , according to the current speed v of the vehicle car , calculate the longitudinal distance T pre_c ×v car At , the expected predicted lateral distance is:

[0219] D pre_c =a tr_0 +a tr_1 *(T pre_c *v car )+a tr_2 *(T pre_c *v car ) 2

[0220] A. Lane change direction is left

[0221] If the expected predicted lateral distance D pre_c In the range (-1, +∞], or D1 in the range (-Th w_st ,1], and continuous Thc_time If the above conditions are met within the time, the lane changing driving sub-state of "lane changing" is canceled and the lane changing driving sub-state of "lane changing failed" is output.

[0222] B. Change lane to the right

[0223] If the expected predicted lateral distance D pre_c In the range [-∞, 1), or D1 in the range [-1, Th w_st ], and continuous Th c_time If the above conditions are met within the time, the lane changing driving sub-state of "lane changing" is canceled and the lane changing driving sub-state of "lane changing failed" is output.

[0224] When the target vehicle completes lane change, if the target vehicle crosses the lane line between the new lane and the original lane, that is, the latest data D1 and D2 stored in the current frame meet the following conditions:

[0225] D1*D2<0,D1≠±1

[0226] The driving state of the target vehicle can be set to the lane change driving sub-state of "lane change failure".

[0227] In addition, a time threshold Th for the lane change pre-completion state to last can be set k_time , if the ego vehicle meets one of the following conditions in the new lane, the driving state of the target vehicle can be set to the lane change driving sub-state of lane change completion:

[0228] A.D1 ranges from [-Th w_st ,Th w_st ]Inside;

[0229] B. The "Lane Change Pre-Complete" state lasts for Th k_time time.

[0230] When the target vehicle completes the lane change, the driving state of the target vehicle may be set from the lane change driving sub-state of "lane change completed" to the state of "driving along the standard lane".

[0231] When the target vehicle fails to change lanes, the driving state of the target vehicle may be set from the lane change driving sub-state of "lane change failure" to the state of "driving along the standard lane".

[0232] In this way, the target vehicle's historical trajectory can be curve fitted to predict the target vehicle's own driving trajectory, so that based on the target vehicle's driving trajectory and the reference lane line, the positional relationship between the target vehicle and the reference lane line can be accurately calculated, and the sub-state stage changes of the target vehicle's lane change driving state can be accurately calculated based on the positional relationship between the target vehicle and the reference lane line, thereby improving the accuracy of driving state prediction.

[0233] In one embodiment, there may be multiple ways to determine whether the target vehicle is in a large curve driving state based on the lane line state and the vehicle driving information. For example, in the standard lane state, there are reference lane lines on both sides of the target vehicle. When the lane line state of the target vehicle is in the standard lane state, the lane curvature of the reference lane line may be calculated; if the lane curvature is greater than a preset curvature threshold and the lane line state of the target vehicle is in the standard lane state within a second preset time period, it is determined that the target vehicle is in a large curve driving state.

[0234] Among them, the lane curvature can be the curvature of the reference lane line, and the preset curvature threshold can be a pre-set curvature threshold, which can be used to determine whether the target vehicle is in a large curve driving state. The specific value of the preset curvature threshold can be set according to actual conditions.

[0235] Among them, there are many ways to calculate the lane curvature of the reference lane line. For example, the farthest effective longitudinal coordinate of the target vehicle can be determined based on the lane line information of the reference lane line. The lane line slopes corresponding to the reference lane lines on both sides of the target vehicle at the farthest effective longitudinal coordinate can be calculated based on the lane line equations of the reference lane lines on both sides of the target vehicle. The lane curvature can be calculated based on the lateral distance between the reference lane lines on both sides and the target vehicle and the lane line slope.

[0236] Among them, the farthest effective ordinate is the farthest effective distance X of the x coordinate effi .

[0237] Among them, based on the lane line equations of the reference lane lines on both sides of the target vehicle, the lane line slopes corresponding to the reference lane lines on both sides at the farthest effective ordinate are calculated, and the lane line slope y′1 of the reference lane line on the left can be obtained as:

[0238] y′ l =a l_1 +2*a l_2 X effi +3*a l_3 X effi 2

[0239] And get the lane slope y′ of the reference lane on the right r for:

[0240] y′ r =a r_1 +2*a r_2 X effi +3*a r_3 X effi 2

[0241] A lateral offset weight coefficient C less than 1 can be set w The lateral offset weight coefficient can be a preset coefficient used to calculate the curvature weight corresponding to each reference lane line. The specific value of the coefficient can be set according to the actual situation, and the embodiment of the present application does not limit it here. Thus, the lateral offset factor can be calculated:

[0242]

[0243] Different calculations are performed on large curves according to the slopes of the reference lanes on both sides:

[0244] (1) In y′ l ≥0 and y′ r ≥0, the lateral offset weight coefficient C w And the lateral offset factor is used to calculate the curvature weights of the lane lines on the left and right sides:

[0245] W l =C w +C offset

[0246] W r =(1-C w )-C offset

[0247] Where W1 is the curvature weight of the left lane line, W r The curvature weight of the lane line on the right side can be calculated based on the curvature weights of the lane lines on the left and right sides. The curvature weights of the lane lines on the left and right sides are added together to be equal to 1. Therefore, the lane curvature of the entire lane can be calculated based on the curvature weights of the lane lines on the left and right sides:

[0248] Cur=2*(W1*a l_2 +W r *a r_2 )

[0249] (2) When y′1≤0 and y′ r ≤0, the lateral offset weight coefficient C w And the lateral offset factor is used to calculate the curvature weights of the lane lines on the left and right sides:

[0250] W1=(1-C w )+C offset

[0251] W r =C w -C offset

[0252] Therefore, the lane curvature of the entire lane can be calculated based on the curvature weights of the left and right lane lines:

[0253] Cur=2*(W1*a l_2 +W r *a r_2 )

[0254] (3) For other cases, the lane curvature of the entire lane can be calculated using the following formula:

[0255] Cur=2*(a l_2 +a r_2 )

[0256] Then, the preset curvature threshold Th for entering the large curve driving state can be set G , the curvature threshold value Th for exiting the “big curve state” S The second preset duration Th of the state k_time , where Th G >Th S , if the lane curvature cur is greater than the preset curvature threshold Th G , and for a continuous period of time Th k_time The lane line state of the target vehicle is in the standard lane state, and it is determined that the target vehicle is still in a large curve driving state, otherwise the timing is reset.

[0257] If the target vehicle is already in a state of driving on a wide curve, it can be determined that the target vehicle is not in a state of driving on a wide curve when one of the following conditions occurs:

[0258] The lane where the target vehicle is located is not in the "standard lane state";

[0259] The lane curvature cur is less than the curvature threshold Th S , and the continuous time Th k_time All curvature data satisfy this threshold condition.

[0260] In one embodiment, when the driving state of the target vehicle does not belong to the driving state of crossing the line, the driving state of following the line, the driving state of changing lanes, and the driving state of a large curve, it can be determined that the driving state of the target vehicle belongs to the driving state along the steering wheel trajectory.

[0261] The driving state along the steering wheel track may indicate that the target vehicle is not driving along the lane line.

[0262] In one embodiment, please refer to Figure 4 , Figure 4It is a specific flow chart of a driving state prediction method provided in an embodiment of the present application. During the driving process of the target vehicle, the lane line information around the target vehicle can be obtained through visual perception technology, so that the reference lane lines on the left and right sides of the target vehicle can be screened according to the lane lines provided in the lane line information, and the lane width between the reference lane lines can be calculated based on the geometric characteristics of the reference lane lines to judge the validity of the lane width, so as to determine the lane line state of the target vehicle. In addition, the driving state of the target vehicle on the line can be judged according to the reference lane line and the vehicle driving information to judge whether the target vehicle is in the driving state of the line on the line. When the target vehicle is judged to be in the driving state of the line on the line, the target vehicle is output to be in the driving state of the line on the line. When the target vehicle is not in the driving state of the line on the line, the next driving state judgment can be made according to whether the lane line state of the reference lane line is valid (standard lane state). Specifically, when the target vehicle is not in the driving state of the line on the line, the driving state of the target vehicle can be further determined according to the lane line state. For example, when the lane line state belongs to the standard lane state, it can be determined based on the vehicle driving information and the lane line information of the reference lane line whether the target vehicle belongs to the lane change driving state, so that the lane change driving state processing can be performed to further determine the lane change driving sub-state and other lane change related states of the target vehicle. When the target vehicle is not in the driving state of the line on the line, and the lane line state belongs to the non-standard lane state, it can be determined based on the vehicle driving information and the lane line information whether the target vehicle belongs to the driving state along the single-side lane line. When driving along the single-side lane line, it can be output that the target vehicle belongs to the driving state along the line and the corresponding lane line along. At the same time, the target vehicle can also be judged on the state of driving on a large curve to determine whether the target vehicle is still in the state of driving on a large curve. When the target vehicle is not in the state of driving on the line, changing lanes, driving along the line, or driving on a large curve, it can be output that the target vehicle is in the state of driving along the steering wheel track.

[0263] In this way, the embodiment of the present application can determine the driving state of the target vehicle only based on the vehicle driving information and lane line information of the target vehicle. Compared with the method based on state extraction and deep learning prediction, the embodiment of the present application has low computing power requirements, simple process, and no need for complex modeling or network construction. At the same time, the embodiment of the present application is oriented to the Advanced Driving Assistance System (ADAS), mainly for conventional structured road scenes, and establishes the connection between the vehicle and the environmental information through the vehicle driving information and lane line information of the target vehicle, accurately obtains the relationship between the target vehicle and the lane line in the actual driving scene, conforms to the subjective driving experience of people and the constraints of the lane line on the vehicle driving in the assisted driving, and calculates the various driving states of the vehicle based on the road lane line in detail, which can achieve accurate prediction of the driving state of the target vehicle in various driving scenes on the basis of low calculation amount. In addition, for new driving state prediction requirements, the embodiment of the present application can simply perform logical modification or addition, and the algorithm logic is completely traceable, and has high stability and adaptability to the conventional road environment, further improving the efficiency of driving state prediction.

[0264] In order to facilitate better implementation of the driving state prediction method provided in the embodiment of the present application, the embodiment of the present application also provides a device based on the above driving state prediction method. The meanings of the terms are the same as those in the above driving state prediction method, and the specific implementation details can refer to the description in the method embodiment.

[0265] For example, Figure 5 As shown, it is a schematic diagram of the structure of the driving state prediction device provided in an embodiment of the present application. The driving state prediction device may include a data acquisition module 201 and a driving state determination module 202, as follows:

[0266] The data acquisition module 201 is used to acquire the vehicle driving information and lane line information of the target vehicle;

[0267] The driving state determination module 202 is used to determine the driving state of the target vehicle based on the lane line based on the vehicle driving information and the lane line information.

[0268] In one embodiment, the driving state determination module 202 includes:

[0269] A reference lane line determination submodule, used to determine a reference lane line adjacent to the target vehicle on the lane based on the lane line information;

[0270] The driving state judgment submodule is used to determine the driving state of the target vehicle based on the lane line based on the reference lane line and the vehicle driving information.

[0271] In one embodiment, the driving state determination submodule includes:

[0272] A first trajectory equation determining unit, used to determine a first target historical trajectory equation based on a reference lane line and vehicle driving information;

[0273] The first driving state determination unit is used to determine the driving state of the target vehicle based on the first target historical trajectory equation.

[0274] In one embodiment, the first trajectory equation determining unit includes:

[0275] A first distance acquisition subunit is used to acquire a first driving distance and a first lateral distance according to a lane line equation of a reference lane line and vehicle driving information, wherein the first driving distance is a distance traveled by the target vehicle between a first moment and a second moment, and the first lateral distance is a distance between the target vehicle and the reference lane line at the second moment;

[0276] The trajectory equation determination subunit is used to determine a trajectory curve of a historical trajectory of the target vehicle based on the first driving distance and the first lateral distance, and obtain a first target historical trajectory equation.

[0277] In one embodiment, the trajectory equation determination subunit includes:

[0278] Acquire a first angle value, where the first angle value indicates an angle between a driving direction of the target vehicle and a reference lane line at a second moment;

[0279] If the absolute value of the first lateral distance is less than the first preset distance threshold and the absolute value of the first angle value is less than the first preset angle threshold, the curve of the historical trajectory of the target vehicle is determined based on the first driving distance and the first lateral distance to obtain the first target historical trajectory equation.

[0280] In one embodiment, if the absolute value of the first lateral distance is less than the first preset distance threshold and the absolute value of the first angle value is less than the first preset angle threshold, then based on the first driving distance and the first lateral distance, a curve of the historical trajectory of the target vehicle is determined to obtain the first target historical trajectory equation, specifically including:

[0281] Obtaining a second lateral distance, where the second lateral distance is a distance between the target vehicle and the reference lane line at a preset longitudinal distance in front of the target vehicle, predicted by a lane line equation of the reference lane line;

[0282] If the absolute value of the first lateral distance is less than the first preset distance threshold and the absolute value of the first angle value is less than the first preset angle threshold, and the second lateral distance is not greater than the second preset distance threshold, based on the first driving distance and the first lateral distance, the quadratic curve of the historical trajectory of the target vehicle is determined to obtain the first target historical trajectory equation.

[0283] In one embodiment, the driving state determination submodule includes:

[0284] A neighboring reference lane line determination unit, used to determine a neighboring reference lane line of the target vehicle among the reference lane lines;

[0285] The first driving state judgment unit is used to judge whether the target vehicle is in a lane-crossing driving state based on the adjacent reference lane line and the vehicle driving information.

[0286] In one embodiment, the driving state includes at least one of a driving state along a line, a lane change driving state, and a large curve driving state, and the driving state judgment submodule includes:

[0287] A lane line state determination unit, used to determine the lane line state of the target vehicle based on the reference lane line, the lane line state including the standard lane state and the non-standard lane line state;

[0288] The second driving state judgment unit is used to determine whether the target vehicle is in at least one of the driving states of along-line driving, lane-changing driving, and wide-curve driving based on the lane line state and vehicle driving information.

[0289] In one embodiment, the lane line state determination unit is used to:

[0290] If the target vehicle lacks a reference lane line on at least one side, it is determined that the lane line state of the target vehicle belongs to a non-standard lane state;

[0291] If there are reference lane lines on both sides of the target vehicle and the lane width between the reference lane lines is within the preset lane width range, it is determined that the lane line state of the target vehicle belongs to the standard lane state;

[0292] If there are reference lane lines on both sides of the target vehicle and the lane width between the reference lane lines is not within the preset lane width range, it is determined that the lane line state of the target vehicle belongs to a non-standard lane state.

[0293] In one embodiment, the second driving state determination unit includes:

[0294] A lane-traveling state determination subunit, used to determine whether the target vehicle is in a lane-traveling state based on the vehicle driving information and the lane line information of the reference lane line when the lane line state belongs to a non-standard lane state;

[0295] The lane change driving state determination subunit is used to determine whether the target vehicle is in the lane change driving state based on the vehicle driving information and the lane line information of the reference lane line when the lane line state belongs to the standard lane state.

[0296] In one embodiment, the route-travel status determination subunit is used to:

[0297] Based on the vehicle driving information, a curve of the historical trajectory of the target vehicle in the vehicle coordinate system of the target vehicle is obtained to obtain a second target historical trajectory equation;

[0298] Based on the second target historical trajectory equation and the lane line equation of the reference lane line, it is determined whether the target vehicle is in a driving state along the current reference lane line.

[0299] In one embodiment, in a standard lane state, there are reference lane lines on both sides of the target vehicle, and the step of determining whether the target vehicle is in a lane change driving state based on the vehicle driving information and the lane line information of the reference lane lines specifically includes:

[0300] Based on the lane line equation of the reference lane line, a second angle value is obtained, where the second angle value indicates the angles between the reference lane lines on both sides of the target vehicle and the driving direction of the target vehicle;

[0301] If the absolute values ​​of the second angle values ​​are respectively less than the corresponding second preset angle thresholds, and the continuous time that the target vehicle is in the standard lane state exceeds the first preset time, based on the vehicle driving information and the lane line information, a curve of the historical trajectory of the target vehicle is obtained to obtain a third target historical trajectory equation;

[0302] Based on the third target historical trajectory equation, it is determined whether the target vehicle is in a lane-changing driving state.

[0303] In some embodiments, the step of determining whether the target vehicle is in a lane-changing driving state based on the third target historical trajectory equation specifically includes:

[0304] Based on the third target history trajectory equation, it is determined whether the target vehicle belongs to one of the multiple lane change driving sub-states included in the lane change driving state, and the lane change driving sub-states include: driving along the standard lane, changing lanes, lane change pre-completion, lane change completion and lane change failure.

[0305] In one embodiment, the step of obtaining the curve of the historical trajectory of the target vehicle based on the vehicle driving information and the lane line information to obtain the third target historical trajectory equation specifically includes:

[0306] Acquire a second driving distance of the target vehicle within a preset update time period based on the vehicle driving information;

[0307] According to the lane line equations of the reference lane lines on both sides of the target vehicle, the lateral distance between the reference lane line and the target vehicle at the end of the preset update time is determined to obtain the left lateral distance and the right lateral distance;

[0308] Normalize the left lateral distance and the right lateral distance to obtain the relative lateral distance;

[0309] According to the relative lateral distance and the second driving distance, a curve of the historical trajectory of the target vehicle is fitted to obtain a third target historical trajectory equation.

[0310] In one embodiment, in a standard lane state, there are reference lane lines on both sides of the target vehicle, and the second driving state judgment unit is used to:

[0311] A lane curvature calculation subunit, used for calculating the lane curvature of the reference lane line when the lane line state of the target vehicle is in a standard lane state;

[0312] The driving state determination subunit is used to determine that the target vehicle is in a large curve driving state if the lane curvature is greater than a preset curvature threshold and the lane line state of the target vehicle is in a standard lane state within a second preset time length.

[0313] In one embodiment, the lane curvature calculation subunit is used to:

[0314] Determine the farthest effective longitudinal coordinate of the target vehicle based on the lane line information of the reference lane line;

[0315] Based on the lane line equations of the reference lane lines on both sides of the target vehicle, the lane line slopes corresponding to the reference lane lines on both sides at the farthest effective ordinate are calculated;

[0316] The lane curvature is calculated based on the lateral distance between the reference lane lines on both sides and the target vehicle and the slope of the lane lines.

[0317] In one embodiment, the driving state prediction device further includes a driving state determination module along the steering wheel trajectory, which is used to:

[0318] When the driving state of the target vehicle does not belong to the driving state of crossing the line, the driving state of following the line, the driving state of changing lanes, and the driving state of a large curve, it is determined that the driving state of the target vehicle belongs to the driving state of following the steering wheel trajectory.

[0319] As can be seen from the above, the embodiment of the present application obtains the vehicle driving information and lane line information of the target vehicle through the data acquisition module 201; the driving state determination module 202 determines the driving state of the target vehicle based on the lane line based on the vehicle driving information and lane line information. In this way, the embodiment of the present application can determine the driving state of the target vehicle only based on the vehicle driving information and lane line information of the target vehicle, without relying on complex modeling or network construction, and establish a connection between the vehicle and environmental information through the vehicle driving information and lane line information of the target vehicle, and accurately obtain the relationship between the target vehicle and the lane line in the actual driving scene, so as to achieve accurate determination of the driving state of the target vehicle in the actual driving scene on the basis of low calculation amount, thereby improving the driving state prediction efficiency.

[0320] Accordingly, the embodiment of the present application also provides a vehicle-mounted terminal, such as Figure 6 As shown, Figure 6 A schematic diagram of the structure of the vehicle-mounted terminal provided in an embodiment of the present application. The vehicle-mounted terminal 300 includes a processor 301 having one or more processing cores, a memory 302 having one or more computer-readable storage media, and a computer program stored in the memory 302 and executable on the processor. The processor 301 is electrically connected to the memory 302. Those skilled in the art will appreciate that the vehicle-mounted terminal structure shown in the figure does not constitute a limitation on the vehicle-mounted terminal, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.

[0321] The processor 301 is the control center of the vehicle terminal 300, and uses various interfaces and lines to connect various parts of the entire vehicle terminal 300. It executes various functions and processes data of the vehicle terminal 300 by running or loading software programs and / or units stored in the memory 302, and calling data stored in the memory 302. The processor 301 can be a processor CPU, a graphics processor GPU, a network processor (Network Processor, NP), etc., and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0322] In the embodiment of the present application, the processor 301 in the vehicle terminal 300 will load instructions corresponding to the processes of one or more application programs into the memory 302 according to the following steps, and the processor 301 will run the application programs stored in the memory 302 to implement various functions, such as:

[0323] Obtain vehicle driving information and lane line information of the target vehicle; based on the vehicle driving information and lane line information, determine the driving state of the target vehicle based on the lane line.

[0324] Furthermore, various functions implemented by running the application program stored in the memory 302 can also be found in the description of the aforementioned embodiment, which will not be repeated here.

[0325] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0326] Optional, such as Figure 6 As shown, the vehicle terminal 300 also includes: a touch screen 303, a radio frequency circuit 304, an audio circuit 305, an input unit 306 and a power supply 307. Among them, the processor 301 is electrically connected to the touch screen 303, the radio frequency circuit 304, the audio circuit 305, the input unit 306 and the power supply 307 respectively. Those skilled in the art can understand that Figure 6The vehicle-mounted terminal structure shown in the figure does not constitute a limitation on the vehicle-mounted terminal, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0327] The touch display screen 303 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The touch display screen 303 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the vehicle terminal, which can be composed of graphics, text, icons, videos and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD, Liquid Crystal Display), an organic light-emitting diode (OLED, Organic Light-Emitting Diode), etc. The touch panel can be used to collect the user's touch operation on or near it (such as the user uses any suitable object or accessory such as a finger, stylus, etc. on the touch panel or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute the corresponding program. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch direction, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 301, and can receive the command sent by the processor 301 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 301 to determine the type of touch event, and then the processor 301 provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the touch display screen 303 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the touch display screen 303 can also be used as a part of the input unit 306 to realize the input function.

[0328] The RF circuit 304 may be used to send and receive RF signals, so as to establish wireless communication with a network device or other vehicle-mounted terminals through wireless communication, and to send and receive signals with the network device or other vehicle-mounted terminals.

[0329] The audio circuit 305 can be used to provide an audio interface between the user and the vehicle-mounted terminal through a speaker and a microphone. The audio circuit 305 can transmit the electrical signal converted from the received audio data to the speaker, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 305 and converted into audio data, and then the audio data is output to the processor 301 for processing, and then sent to another vehicle-mounted terminal through the radio frequency circuit 304, or the audio data is output to the memory 302 for further processing. The audio circuit 305 may also include an earplug jack to provide communication between an external headset and the vehicle-mounted terminal.

[0330] The input unit 306 may be used to receive input target video and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0331] The power supply 307 is used to supply power to various components of the vehicle-mounted terminal 300. Optionally, the power supply 307 can be logically connected to the processor 301 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 307 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0332] although Figure 6 Not shown, the vehicle terminal 300 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.

[0333] In the above embodiments, the description of each embodiment has its own emphasis. For the parts not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. It should be noted that the vehicle-mounted terminal provided in the embodiment of the present application and the driving state prediction method in the above embodiment belong to the same concept. The specific implementation process is detailed in the above method embodiment and will not be repeated here.

[0334] As can be seen from the above, the vehicle-mounted terminal provided in the embodiment of the present application can obtain the vehicle driving information and lane line information of the target vehicle; based on the vehicle driving information and lane line information, determine the driving state of the target vehicle based on the lane line. In this way, the embodiment of the present application can determine the driving state of the target vehicle only based on the vehicle driving information and lane line information of the target vehicle, without relying on complex modeling or network construction, and establish a connection between the vehicle and environmental information through the vehicle driving information and lane line information of the target vehicle, and accurately obtain the relationship between the target vehicle and the lane line in the actual driving scene, so as to accurately determine the driving state of the target vehicle in the actual driving scene on the basis of low calculation amount, thereby improving the driving state prediction efficiency.

[0335] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0336] To this end, an embodiment of the present application provides a computer-readable storage medium, which includes a computer program. When the computer program is run on a vehicle-mounted terminal, the computer program is used to enable the vehicle-mounted terminal to execute any of the driving state prediction methods provided in the embodiments of the present application. For example, the computer program can execute the following steps of the driving state prediction method:

[0337] Obtain vehicle driving information and lane line information of the target vehicle; based on the vehicle driving information and lane line information, determine the driving state of the target vehicle based on the lane line.

[0338] Furthermore, for the detailed steps of the above method steps, reference can be made to the description in the above embodiments, which will not be repeated here.

[0339] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0340] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0341] Since the computer program stored in the computer-readable storage medium can execute any one of the driving state prediction methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the driving state prediction methods provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0342] According to one aspect of the present application, a computer program product is also provided, including a computer program, which is stored in a computer-readable storage medium; when the processor of a vehicle-mounted terminal reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the vehicle-mounted terminal executes the methods provided in the various optional implementations of the above-mentioned embodiments.

[0343] In the above-mentioned driving state prediction device, computer-readable storage medium, vehicle-mounted terminal, and computer program product embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and beneficial effects of the driving state prediction device, computer-readable storage medium, computer program product, vehicle-mounted terminal and its corresponding units described above can refer to the description of the driving state prediction method in the above embodiment, and will not be repeated here.

[0344] The above is a detailed introduction to a driving state prediction method, device, vehicle-mounted terminal, vehicle, computer-readable storage medium and computer program product provided in an embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A driving state prediction method, characterized in that: include: Obtain vehicle driving information and lane line information of the target vehicle; Based on the vehicle driving information and the lane line information, a driving state of the target vehicle based on the lane line is determined.

2. The driving state prediction method according to claim 1, characterized in that: The determining, based on the vehicle driving information and the lane line information, the driving state of the target vehicle based on the lane line includes: Based on the lane line information, determining a reference lane line adjacent to the target vehicle on the lane; Based on the reference lane line and the vehicle driving information, a driving state of the target vehicle based on the lane line is determined.

3. The driving state prediction method according to claim 2, characterized in that: The determining, based on the reference lane line and the vehicle driving information, the driving state of the target vehicle based on the lane line comprises: Determining a first target historical trajectory equation based on the reference lane line and the vehicle driving information; Based on the first target historical trajectory equation, a driving state of the target vehicle is determined.

4. The driving state prediction method according to claim 3, characterized in that: The determining of a first target historical trajectory equation based on the reference lane line and the vehicle driving information includes: According to the lane line equation of the reference lane line and the vehicle driving information, a first driving distance and a first lateral distance are acquired, wherein the first driving distance is the distance traveled by the target vehicle between a first moment and a second moment, and the first lateral distance is the distance between the target vehicle and the reference lane line at the second moment; Based on the first driving distance and the first lateral distance, a trajectory curve of the historical trajectory of the target vehicle is determined to obtain a first target historical trajectory equation.

5. The driving state prediction method according to claim 4, characterized in that: The step of determining a trajectory curve of a historical trajectory of the target vehicle based on the first driving distance and the first lateral distance to obtain a first target historical trajectory equation includes: Acquire a first angle value, where the first angle value indicates an angle between the driving direction of the target vehicle and the reference lane line at the second moment; If the absolute value of the first lateral distance is less than a first preset distance threshold and the absolute value of the first angle value is less than a first preset angle threshold, a curve of the historical trajectory of the target vehicle is determined based on the first driving distance and the first lateral distance to obtain a first target historical trajectory equation.

6. The driving state prediction method according to claim 5, characterized in that: If the absolute value of the first lateral distance is less than a first preset distance threshold and the absolute value of the first angle value is less than a first preset angle threshold, a curve of the historical trajectory of the target vehicle is determined based on the first driving distance and the first lateral distance to obtain a first target historical trajectory equation, including: Acquire a second lateral distance, where the second lateral distance is a distance between the target vehicle and the reference lane line at a preset longitudinal distance in front of the target vehicle, predicted by a lane line equation of the reference lane line; If the absolute value of the first lateral distance is less than a first preset distance threshold and the absolute value of the first angle value is less than a first preset angle threshold, and the second lateral distance is not greater than a second preset distance threshold, based on the first driving distance and the first lateral distance, the quadratic curve of the historical trajectory of the target vehicle is determined to obtain a first target historical trajectory equation.

7. The driving state prediction method according to claim 2, characterized in that: The driving state includes a lane-crossing driving state, and determining the driving state of the target vehicle based on the lane line based on the reference lane line and the vehicle driving information includes: Determining a neighboring reference lane line of the target vehicle among the reference lane lines; Based on the neighboring reference lane line and the vehicle driving information, it is determined whether the target vehicle is in a lane-crossing driving state.

8. The driving state prediction method according to claim 2, characterized in that: The driving state includes at least one of a driving state along a line, a lane change driving state, and a large curve driving state. The determining, based on the reference lane line and the vehicle driving information, the driving state of the target vehicle based on the lane line includes: Determine the lane line state of the target vehicle based on the reference lane line, wherein the lane line state includes a standard lane state and a non-standard lane line state; Based on the lane line state and the vehicle driving information, it is determined whether the target vehicle is in at least one of a driving state along the line, a lane changing driving state, and a large curve driving state.

9. The driving state prediction method according to claim 8, characterized in that: The determining the lane line state of the target vehicle based on the reference lane line includes: If the target vehicle lacks a reference lane line on at least one side, determining that the lane line state of the target vehicle belongs to a non-standard lane state; If there are reference lane lines on both sides of the target vehicle and the lane width between the reference lane lines is within a preset lane width range, it is determined that the lane line state of the target vehicle belongs to the standard lane state; If there are reference lane lines on both sides of the target vehicle and the lane width between the reference lane lines is not within a preset lane width range, it is determined that the lane line state of the target vehicle belongs to a non-standard lane state.

10. The driving state prediction method according to claim 8, characterized in that: Determining whether the target vehicle is in a lane-along driving state or a lane-changing driving state based on the lane line state and the vehicle driving information includes: When the lane line state belongs to a non-standard lane state, determining whether the target vehicle belongs to a lane-along driving state based on the vehicle driving information and the lane line information of the reference lane line; When the lane line state belongs to the standard lane state, it is determined whether the target vehicle belongs to the lane changing driving state based on the vehicle driving information and the lane line information of the reference lane line.

11. The driving state prediction method according to claim 10, characterized in that: The determining whether the target vehicle is in a driving state along the lane based on the vehicle driving information and the lane line information of the reference lane line includes: Based on the vehicle driving information, a curve of the historical trajectory of the target vehicle in the vehicle coordinate system of the target vehicle is obtained to obtain a second target historical trajectory equation; Based on the second target historical trajectory equation and the lane line equation of the reference lane line, it is determined whether the target vehicle is in a driving state along the current reference lane line.

12. The driving state prediction method according to claim 10, characterized in that: In the standard lane state, there are reference lane lines on both sides of the target vehicle, and determining whether the target vehicle is in a lane-changing driving state based on the vehicle driving information and the lane line information of the reference lane lines includes: Based on the lane line equation of the reference lane line, obtaining a second angle value, where the second angle value indicates the angles between the reference lane lines on both sides of the target vehicle and the driving direction of the target vehicle; If the absolute values ​​of the second angle values ​​are respectively less than the corresponding second preset angle thresholds, and the continuous duration of the target vehicle being in the standard lane state exceeds the first preset duration, based on the vehicle driving information and the lane line information, a curve of the historical trajectory of the target vehicle is obtained to obtain a third target historical trajectory equation; Based on the third target historical trajectory equation, it is determined whether the target vehicle is in a lane-changing driving state.

13. The driving state prediction method according to claim 12, characterized in that: The determining, based on the third target historical trajectory equation, whether the target vehicle is in a lane-changing driving state comprises: Based on the third target historical trajectory equation, it is determined whether the target vehicle belongs to one of a plurality of lane changing driving sub-states included in the lane changing driving state, wherein the lane changing driving sub-states include: driving along a standard lane, changing lanes, lane change pre-completion, lane change completion, and lane change failure.

14. The driving state prediction method according to claim 12, characterized in that: The step of acquiring a curve of the historical trajectory of the target vehicle based on the vehicle driving information and the lane line information to obtain a third target historical trajectory equation includes: Acquire a second driving distance of the target vehicle within a preset update time period based on the vehicle driving information; According to lane line equations of reference lane lines on both sides of the target vehicle, determining the lateral distance between the reference lane line and the target vehicle at the end of the preset update time, and obtaining the left lateral distance and the right lateral distance; Normalizing the left lateral distance and the right lateral distance to obtain a relative lateral distance; A curve of the historical trajectory of the target vehicle is fitted according to the relative lateral distance and the second driving distance to obtain a third target historical trajectory equation.

15. The driving state prediction method according to claim 8, characterized in that: In the standard lane state, there are reference lane lines on both sides of the target vehicle, and determining whether the target vehicle is in a wide curve driving state based on the lane line state and the vehicle driving information includes: When the lane line state of the target vehicle is in a standard lane state, calculating the lane curvature of the reference lane line; If the lane curvature is greater than a preset curvature threshold and the lane line state of the target vehicle is in a standard lane state within a second preset time length, it is determined that the target vehicle is in a large curve driving state.

16. The driving state prediction method according to claim 15, characterized in that: The calculating the lane curvature of the reference lane line includes: Determine the farthest effective longitudinal coordinate of the target vehicle based on the lane line information of the reference lane line; Based on the lane line equations of the reference lane lines on both sides of the target vehicle, the lane line slopes corresponding to the reference lane lines on both sides at the farthest effective ordinate are calculated; The lane curvature is calculated based on the lateral distance between the reference lane lines on both sides and the target vehicle and the slope of the lane lines.

17. The driving state prediction method according to any one of claims 1 to 16, characterized in that: The method further comprises: When the driving state of the target vehicle does not belong to the driving state of crossing the line, the driving state of following the line, the driving state of changing lanes, and the driving state of a large curve, it is determined that the driving state of the target vehicle belongs to the driving state of following the steering wheel trajectory.

18. A driving state prediction device, characterized in that: include: A data acquisition module, used to acquire vehicle driving information and lane line information of a target vehicle; A driving state determination module is used to determine the driving state of the target vehicle based on the lane line based on the vehicle driving information and the lane line information.

19. A vehicle-mounted terminal, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of any one of the methods of claims 1 to 17.

20. A vehicle, characterized in that: The vehicle includes the vehicle-mounted terminal as claimed in claim 19.

21. A computer-readable storage medium, characterized in that: It includes a computer program. When the computer program is run on a vehicle-mounted terminal, the computer program is used to enable the vehicle-mounted terminal to execute the steps of any method described in claims 1 to 17.

Images